Veronica-Polymorphic 551M — Pretrained v1
Browse files- added_tokens.json +16 -0
- config.json +32 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- trainer_state.json +2657 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 50261,
|
| 3 |
+
"<|bos|>": 50257,
|
| 4 |
+
"<|code|>": 50268,
|
| 5 |
+
"<|document|>": 50264,
|
| 6 |
+
"<|endofchunk|>": 50270,
|
| 7 |
+
"<|observation|>": 50263,
|
| 8 |
+
"<|pad|>": 50258,
|
| 9 |
+
"<|retrieval|>": 50265,
|
| 10 |
+
"<|scratchpad|>": 50266,
|
| 11 |
+
"<|sep|>": 50269,
|
| 12 |
+
"<|system|>": 50259,
|
| 13 |
+
"<|thought|>": 50267,
|
| 14 |
+
"<|tool|>": 50262,
|
| 15 |
+
"<|user|>": 50260
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_comment": "Ultra-deep reasoning config: 24L/12H/768d, mlp_mult=4. Maximum reasoning depth for RAG + multi-step inference. ~11-12GB VRAM.",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VeronicaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 50257,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"gradient_checkpointing": true,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"mlp_mult": 4,
|
| 15 |
+
"model_type": "veronica",
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_funcs": 3,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 50258,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"router_aux_weight": 0.015999763124389305,
|
| 25 |
+
"router_dim": 128,
|
| 26 |
+
"router_tau": 1.400028804954452,
|
| 27 |
+
"transformers_version": "4.57.0.dev0",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"use_channel_attention": false,
|
| 30 |
+
"use_flash_attn": true,
|
| 31 |
+
"vocab_size": 50271
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50258,
|
| 8 |
+
"transformers_version": "4.57.0.dev0"
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:809ed2aff4a95bff277106992f002be0e789ad07b108eb62ca33dcd9e6952879
|
| 3 |
+
size 1102824111
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2657 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9999925976919604,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 33773,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.002960923215858705,
|
| 14 |
+
"grad_norm": 41.32149887084961,
|
| 15 |
+
"learning_rate": 1.98e-06,
|
| 16 |
+
"loss": 87.7468,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00592184643171741,
|
| 21 |
+
"grad_norm": 39.51910400390625,
|
| 22 |
+
"learning_rate": 3.98e-06,
|
| 23 |
+
"loss": 85.766,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008882769647576115,
|
| 28 |
+
"grad_norm": 26.557823181152344,
|
| 29 |
+
"learning_rate": 5.98e-06,
|
| 30 |
+
"loss": 80.1376,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.01184369286343482,
|
| 35 |
+
"grad_norm": 21.80652618408203,
|
| 36 |
+
"learning_rate": 7.98e-06,
|
| 37 |
+
"loss": 74.3306,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.014804616079293524,
|
| 42 |
+
"grad_norm": 16.2612247467041,
|
| 43 |
+
"learning_rate": 9.980000000000001e-06,
|
| 44 |
+
"loss": 72.3247,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01776553929515223,
|
| 49 |
+
"grad_norm": 17.281190872192383,
|
| 50 |
+
"learning_rate": 1.198e-05,
|
| 51 |
+
"loss": 71.0703,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.020726462511010933,
|
| 56 |
+
"grad_norm": 16.140579223632812,
|
| 57 |
+
"learning_rate": 1.3980000000000002e-05,
|
| 58 |
+
"loss": 69.5824,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.02368738572686964,
|
| 63 |
+
"grad_norm": 13.456184387207031,
|
| 64 |
+
"learning_rate": 1.598e-05,
|
| 65 |
+
"loss": 67.2135,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.026648308942728342,
|
| 70 |
+
"grad_norm": 11.778711318969727,
|
| 71 |
+
"learning_rate": 1.798e-05,
|
| 72 |
+
"loss": 65.1397,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.02960923215858705,
|
| 77 |
+
"grad_norm": 11.965922355651855,
|
| 78 |
+
"learning_rate": 1.9980000000000002e-05,
|
| 79 |
+
"loss": 63.204,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02960923215858705,
|
| 84 |
+
"eval_loss": 7.691287040710449,
|
| 85 |
+
"eval_runtime": 37.9485,
|
| 86 |
+
"eval_samples_per_second": 28.486,
|
| 87 |
+
"eval_steps_per_second": 7.141,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.032570155374445756,
|
| 92 |
+
"grad_norm": 8.482980728149414,
|
| 93 |
+
"learning_rate": 2.198e-05,
|
| 94 |
+
"loss": 60.9402,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.03553107859030446,
|
| 99 |
+
"grad_norm": 49.948341369628906,
|
| 100 |
+
"learning_rate": 2.398e-05,
|
| 101 |
+
"loss": 58.9346,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03849200180616316,
|
| 106 |
+
"grad_norm": 10.039616584777832,
|
| 107 |
+
"learning_rate": 2.5980000000000002e-05,
|
| 108 |
+
"loss": 57.309,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.041452925022021865,
|
| 113 |
+
"grad_norm": 8.930785179138184,
|
| 114 |
+
"learning_rate": 2.798e-05,
|
| 115 |
+
"loss": 56.3741,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.04441384823788057,
|
| 120 |
+
"grad_norm": 8.14844036102295,
|
| 121 |
+
"learning_rate": 2.998e-05,
|
| 122 |
+
"loss": 55.8969,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.04737477145373928,
|
| 127 |
+
"grad_norm": 16.170246124267578,
|
| 128 |
+
"learning_rate": 3.198e-05,
|
| 129 |
+
"loss": 55.12,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05033569466959798,
|
| 134 |
+
"grad_norm": 10.525145530700684,
|
| 135 |
+
"learning_rate": 3.398e-05,
|
| 136 |
+
"loss": 54.5077,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.053296617885456685,
|
| 141 |
+
"grad_norm": 29.427160263061523,
|
| 142 |
+
"learning_rate": 3.5980000000000004e-05,
|
| 143 |
+
"loss": 54.2087,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.05625754110131539,
|
| 148 |
+
"grad_norm": 47.125083923339844,
|
| 149 |
+
"learning_rate": 3.798e-05,
|
| 150 |
+
"loss": 53.4388,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.0592184643171741,
|
| 155 |
+
"grad_norm": 10.07633113861084,
|
| 156 |
+
"learning_rate": 3.998e-05,
|
| 157 |
+
"loss": 53.5798,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.0592184643171741,
|
| 162 |
+
"eval_loss": 6.5744218826293945,
|
| 163 |
+
"eval_runtime": 38.8407,
|
| 164 |
+
"eval_samples_per_second": 27.832,
|
| 165 |
+
"eval_steps_per_second": 6.977,
|
| 166 |
+
"step": 2000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.0621793875330328,
|
| 170 |
+
"grad_norm": 10.918025970458984,
|
| 171 |
+
"learning_rate": 4.198e-05,
|
| 172 |
+
"loss": 52.5816,
|
| 173 |
+
"step": 2100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.06514031074889151,
|
| 177 |
+
"grad_norm": 12.68106460571289,
|
| 178 |
+
"learning_rate": 4.398e-05,
|
| 179 |
+
"loss": 52.6681,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.06810123396475021,
|
| 184 |
+
"grad_norm": 15.503605842590332,
|
| 185 |
+
"learning_rate": 4.598e-05,
|
| 186 |
+
"loss": 52.5443,
|
| 187 |
+
"step": 2300
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.07106215718060892,
|
| 191 |
+
"grad_norm": 10.995290756225586,
|
| 192 |
+
"learning_rate": 4.798e-05,
|
| 193 |
+
"loss": 51.4841,
|
| 194 |
+
"step": 2400
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.07402308039646761,
|
| 198 |
+
"grad_norm": 22.71038055419922,
|
| 199 |
+
"learning_rate": 4.998e-05,
|
| 200 |
+
"loss": 51.05,
|
| 201 |
+
"step": 2500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.07698400361232632,
|
| 205 |
+
"grad_norm": 11.035310745239258,
|
| 206 |
+
"learning_rate": 5.198e-05,
|
| 207 |
+
"loss": 50.8273,
|
| 208 |
+
"step": 2600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.07994492682818503,
|
| 212 |
+
"grad_norm": 14.107246398925781,
|
| 213 |
+
"learning_rate": 5.398e-05,
|
| 214 |
+
"loss": 50.9043,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.08290585004404373,
|
| 219 |
+
"grad_norm": 11.570377349853516,
|
| 220 |
+
"learning_rate": 5.598e-05,
|
| 221 |
+
"loss": 50.4862,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.08586677325990244,
|
| 226 |
+
"grad_norm": 16.12681770324707,
|
| 227 |
+
"learning_rate": 5.7980000000000004e-05,
|
| 228 |
+
"loss": 50.0248,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.08882769647576114,
|
| 233 |
+
"grad_norm": 14.925129890441895,
|
| 234 |
+
"learning_rate": 5.9980000000000005e-05,
|
| 235 |
+
"loss": 49.789,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.08882769647576114,
|
| 240 |
+
"eval_loss": 6.141844272613525,
|
| 241 |
+
"eval_runtime": 38.2773,
|
| 242 |
+
"eval_samples_per_second": 28.241,
|
| 243 |
+
"eval_steps_per_second": 7.08,
|
| 244 |
+
"step": 3000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.09178861969161985,
|
| 248 |
+
"grad_norm": 16.748519897460938,
|
| 249 |
+
"learning_rate": 6.198e-05,
|
| 250 |
+
"loss": 49.4085,
|
| 251 |
+
"step": 3100
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.09474954290747856,
|
| 255 |
+
"grad_norm": 12.9891939163208,
|
| 256 |
+
"learning_rate": 6.398000000000001e-05,
|
| 257 |
+
"loss": 49.1003,
|
| 258 |
+
"step": 3200
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.09771046612333725,
|
| 262 |
+
"grad_norm": 11.456365585327148,
|
| 263 |
+
"learning_rate": 6.598e-05,
|
| 264 |
+
"loss": 48.6685,
|
| 265 |
+
"step": 3300
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.10067138933919596,
|
| 269 |
+
"grad_norm": 19.153154373168945,
|
| 270 |
+
"learning_rate": 6.798e-05,
|
| 271 |
+
"loss": 48.3342,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.10363231255505466,
|
| 276 |
+
"grad_norm": 13.501580238342285,
|
| 277 |
+
"learning_rate": 6.998e-05,
|
| 278 |
+
"loss": 47.7641,
|
| 279 |
+
"step": 3500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.10659323577091337,
|
| 283 |
+
"grad_norm": 14.034686088562012,
|
| 284 |
+
"learning_rate": 7.198e-05,
|
| 285 |
+
"loss": 47.8053,
|
| 286 |
+
"step": 3600
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.10955415898677208,
|
| 290 |
+
"grad_norm": 14.023058891296387,
|
| 291 |
+
"learning_rate": 7.398e-05,
|
| 292 |
+
"loss": 47.4925,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.11251508220263078,
|
| 297 |
+
"grad_norm": 16.410221099853516,
|
| 298 |
+
"learning_rate": 7.598e-05,
|
| 299 |
+
"loss": 47.1501,
|
| 300 |
+
"step": 3800
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.11547600541848949,
|
| 304 |
+
"grad_norm": 17.547571182250977,
|
| 305 |
+
"learning_rate": 7.798000000000001e-05,
|
| 306 |
+
"loss": 47.3132,
|
| 307 |
+
"step": 3900
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.1184369286343482,
|
| 311 |
+
"grad_norm": 11.753161430358887,
|
| 312 |
+
"learning_rate": 7.998e-05,
|
| 313 |
+
"loss": 47.071,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.1184369286343482,
|
| 318 |
+
"eval_loss": 5.719655990600586,
|
| 319 |
+
"eval_runtime": 38.3575,
|
| 320 |
+
"eval_samples_per_second": 28.182,
|
| 321 |
+
"eval_steps_per_second": 7.065,
|
| 322 |
+
"step": 4000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.12139785185020689,
|
| 326 |
+
"grad_norm": 51.37761306762695,
|
| 327 |
+
"learning_rate": 8.198000000000001e-05,
|
| 328 |
+
"loss": 46.1728,
|
| 329 |
+
"step": 4100
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.1243587750660656,
|
| 333 |
+
"grad_norm": 12.61581802368164,
|
| 334 |
+
"learning_rate": 8.398e-05,
|
| 335 |
+
"loss": 45.9941,
|
| 336 |
+
"step": 4200
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.1273196982819243,
|
| 340 |
+
"grad_norm": 12.667135238647461,
|
| 341 |
+
"learning_rate": 8.598e-05,
|
| 342 |
+
"loss": 46.1649,
|
| 343 |
+
"step": 4300
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.13028062149778302,
|
| 347 |
+
"grad_norm": 10.368157386779785,
|
| 348 |
+
"learning_rate": 8.798e-05,
|
| 349 |
+
"loss": 45.9172,
|
| 350 |
+
"step": 4400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.13324154471364172,
|
| 354 |
+
"grad_norm": 12.5702543258667,
|
| 355 |
+
"learning_rate": 8.998e-05,
|
| 356 |
+
"loss": 45.5541,
|
| 357 |
+
"step": 4500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.13620246792950041,
|
| 361 |
+
"grad_norm": 10.535380363464355,
|
| 362 |
+
"learning_rate": 9.198e-05,
|
| 363 |
+
"loss": 44.45,
|
| 364 |
+
"step": 4600
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.1391633911453591,
|
| 368 |
+
"grad_norm": 11.035446166992188,
|
| 369 |
+
"learning_rate": 9.398e-05,
|
| 370 |
+
"loss": 44.3243,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.14212431436121784,
|
| 375 |
+
"grad_norm": 10.718255043029785,
|
| 376 |
+
"learning_rate": 9.598e-05,
|
| 377 |
+
"loss": 43.8677,
|
| 378 |
+
"step": 4800
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.14508523757707653,
|
| 382 |
+
"grad_norm": 9.816108703613281,
|
| 383 |
+
"learning_rate": 9.798000000000001e-05,
|
| 384 |
+
"loss": 43.6948,
|
| 385 |
+
"step": 4900
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.14804616079293523,
|
| 389 |
+
"grad_norm": 9.837696075439453,
|
| 390 |
+
"learning_rate": 9.998000000000002e-05,
|
| 391 |
+
"loss": 43.6361,
|
| 392 |
+
"step": 5000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.14804616079293523,
|
| 396 |
+
"eval_loss": 5.329010486602783,
|
| 397 |
+
"eval_runtime": 38.0693,
|
| 398 |
+
"eval_samples_per_second": 28.396,
|
| 399 |
+
"eval_steps_per_second": 7.119,
|
| 400 |
+
"step": 5000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.15100708400879395,
|
| 404 |
+
"grad_norm": 10.140490531921387,
|
| 405 |
+
"learning_rate": 0.00010198,
|
| 406 |
+
"loss": 42.8106,
|
| 407 |
+
"step": 5100
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.15396800722465265,
|
| 411 |
+
"grad_norm": 9.330647468566895,
|
| 412 |
+
"learning_rate": 0.00010398,
|
| 413 |
+
"loss": 42.4439,
|
| 414 |
+
"step": 5200
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.15692893044051134,
|
| 418 |
+
"grad_norm": 9.038117408752441,
|
| 419 |
+
"learning_rate": 0.00010598,
|
| 420 |
+
"loss": 41.8943,
|
| 421 |
+
"step": 5300
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.15988985365637007,
|
| 425 |
+
"grad_norm": 10.28738021850586,
|
| 426 |
+
"learning_rate": 0.00010798,
|
| 427 |
+
"loss": 41.5117,
|
| 428 |
+
"step": 5400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.16285077687222876,
|
| 432 |
+
"grad_norm": 9.869328498840332,
|
| 433 |
+
"learning_rate": 0.00010998,
|
| 434 |
+
"loss": 41.3489,
|
| 435 |
+
"step": 5500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.16581170008808746,
|
| 439 |
+
"grad_norm": 10.985088348388672,
|
| 440 |
+
"learning_rate": 0.00011198000000000001,
|
| 441 |
+
"loss": 40.7585,
|
| 442 |
+
"step": 5600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.16877262330394618,
|
| 446 |
+
"grad_norm": 11.46516227722168,
|
| 447 |
+
"learning_rate": 0.00011398,
|
| 448 |
+
"loss": 40.2893,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.17173354651980488,
|
| 453 |
+
"grad_norm": 9.691688537597656,
|
| 454 |
+
"learning_rate": 0.00011598000000000001,
|
| 455 |
+
"loss": 40.0513,
|
| 456 |
+
"step": 5800
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.17469446973566358,
|
| 460 |
+
"grad_norm": 10.819178581237793,
|
| 461 |
+
"learning_rate": 0.00011798,
|
| 462 |
+
"loss": 39.986,
|
| 463 |
+
"step": 5900
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.17765539295152227,
|
| 467 |
+
"grad_norm": 9.694029808044434,
|
| 468 |
+
"learning_rate": 0.00011998,
|
| 469 |
+
"loss": 39.3918,
|
| 470 |
+
"step": 6000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.17765539295152227,
|
| 474 |
+
"eval_loss": 4.900777339935303,
|
| 475 |
+
"eval_runtime": 38.052,
|
| 476 |
+
"eval_samples_per_second": 28.409,
|
| 477 |
+
"eval_steps_per_second": 7.122,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.180616316167381,
|
| 482 |
+
"grad_norm": 9.988055229187012,
|
| 483 |
+
"learning_rate": 0.00011999900481764066,
|
| 484 |
+
"loss": 39.336,
|
| 485 |
+
"step": 6100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.1835772393832397,
|
| 489 |
+
"grad_norm": 13.242379188537598,
|
| 490 |
+
"learning_rate": 0.00011999597899343296,
|
| 491 |
+
"loss": 39.0612,
|
| 492 |
+
"step": 6200
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.1865381625990984,
|
| 496 |
+
"grad_norm": 13.935639381408691,
|
| 497 |
+
"learning_rate": 0.00011999092252825071,
|
| 498 |
+
"loss": 38.585,
|
| 499 |
+
"step": 6300
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.1894990858149571,
|
| 503 |
+
"grad_norm": 9.50368881225586,
|
| 504 |
+
"learning_rate": 0.00011998383559323646,
|
| 505 |
+
"loss": 38.3112,
|
| 506 |
+
"step": 6400
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.1924600090308158,
|
| 510 |
+
"grad_norm": 10.878887176513672,
|
| 511 |
+
"learning_rate": 0.00011997471842825661,
|
| 512 |
+
"loss": 38.3219,
|
| 513 |
+
"step": 6500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1954209322466745,
|
| 517 |
+
"grad_norm": 10.517402648925781,
|
| 518 |
+
"learning_rate": 0.00011996357134189334,
|
| 519 |
+
"loss": 37.8246,
|
| 520 |
+
"step": 6600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.19838185546253323,
|
| 524 |
+
"grad_norm": 10.922290802001953,
|
| 525 |
+
"learning_rate": 0.0001199503947114341,
|
| 526 |
+
"loss": 37.6387,
|
| 527 |
+
"step": 6700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.20134277867839193,
|
| 531 |
+
"grad_norm": 11.845630645751953,
|
| 532 |
+
"learning_rate": 0.00011993518898285887,
|
| 533 |
+
"loss": 37.8343,
|
| 534 |
+
"step": 6800
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.20430370189425062,
|
| 538 |
+
"grad_norm": 8.628484725952148,
|
| 539 |
+
"learning_rate": 0.00011991795467082508,
|
| 540 |
+
"loss": 37.5011,
|
| 541 |
+
"step": 6900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.20726462511010932,
|
| 545 |
+
"grad_norm": 9.489052772521973,
|
| 546 |
+
"learning_rate": 0.00011989869235865012,
|
| 547 |
+
"loss": 37.132,
|
| 548 |
+
"step": 7000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.20726462511010932,
|
| 552 |
+
"eval_loss": 4.595886707305908,
|
| 553 |
+
"eval_runtime": 38.0814,
|
| 554 |
+
"eval_samples_per_second": 28.387,
|
| 555 |
+
"eval_steps_per_second": 7.116,
|
| 556 |
+
"step": 7000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.21022554832596804,
|
| 560 |
+
"grad_norm": 9.687568664550781,
|
| 561 |
+
"learning_rate": 0.00011987740269829175,
|
| 562 |
+
"loss": 36.9362,
|
| 563 |
+
"step": 7100
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.21318647154182674,
|
| 567 |
+
"grad_norm": 8.676931381225586,
|
| 568 |
+
"learning_rate": 0.0001198540864103258,
|
| 569 |
+
"loss": 37.0267,
|
| 570 |
+
"step": 7200
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.21614739475768543,
|
| 574 |
+
"grad_norm": 9.232645988464355,
|
| 575 |
+
"learning_rate": 0.00011982874428392204,
|
| 576 |
+
"loss": 36.5181,
|
| 577 |
+
"step": 7300
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.21910831797354416,
|
| 581 |
+
"grad_norm": 8.917469024658203,
|
| 582 |
+
"learning_rate": 0.00011980137717681727,
|
| 583 |
+
"loss": 36.5812,
|
| 584 |
+
"step": 7400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.22206924118940286,
|
| 588 |
+
"grad_norm": 8.593257904052734,
|
| 589 |
+
"learning_rate": 0.0001197719860152864,
|
| 590 |
+
"loss": 36.0672,
|
| 591 |
+
"step": 7500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.22503016440526155,
|
| 595 |
+
"grad_norm": 10.630696296691895,
|
| 596 |
+
"learning_rate": 0.00011974057179411103,
|
| 597 |
+
"loss": 36.2405,
|
| 598 |
+
"step": 7600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.22799108762112028,
|
| 602 |
+
"grad_norm": 9.975415229797363,
|
| 603 |
+
"learning_rate": 0.00011970713557654582,
|
| 604 |
+
"loss": 35.9903,
|
| 605 |
+
"step": 7700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.23095201083697897,
|
| 609 |
+
"grad_norm": 8.622698783874512,
|
| 610 |
+
"learning_rate": 0.00011967167849428251,
|
| 611 |
+
"loss": 35.8196,
|
| 612 |
+
"step": 7800
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.23391293405283767,
|
| 616 |
+
"grad_norm": 14.828067779541016,
|
| 617 |
+
"learning_rate": 0.00011963420174741161,
|
| 618 |
+
"loss": 35.7946,
|
| 619 |
+
"step": 7900
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.2368738572686964,
|
| 623 |
+
"grad_norm": 9.303028106689453,
|
| 624 |
+
"learning_rate": 0.00011959470660438173,
|
| 625 |
+
"loss": 35.5493,
|
| 626 |
+
"step": 8000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.2368738572686964,
|
| 630 |
+
"eval_loss": 4.408100128173828,
|
| 631 |
+
"eval_runtime": 37.807,
|
| 632 |
+
"eval_samples_per_second": 28.593,
|
| 633 |
+
"eval_steps_per_second": 7.168,
|
| 634 |
+
"step": 8000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.2398347804845551,
|
| 638 |
+
"grad_norm": 11.987268447875977,
|
| 639 |
+
"learning_rate": 0.00011955319440195674,
|
| 640 |
+
"loss": 35.6014,
|
| 641 |
+
"step": 8100
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.24279570370041378,
|
| 645 |
+
"grad_norm": 10.032620429992676,
|
| 646 |
+
"learning_rate": 0.00011950966654517043,
|
| 647 |
+
"loss": 35.5302,
|
| 648 |
+
"step": 8200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.24575662691627248,
|
| 652 |
+
"grad_norm": 9.362653732299805,
|
| 653 |
+
"learning_rate": 0.00011946412450727906,
|
| 654 |
+
"loss": 35.2124,
|
| 655 |
+
"step": 8300
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2487175501321312,
|
| 659 |
+
"grad_norm": 9.706056594848633,
|
| 660 |
+
"learning_rate": 0.00011941656982971138,
|
| 661 |
+
"loss": 34.9229,
|
| 662 |
+
"step": 8400
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.25167847334798993,
|
| 666 |
+
"grad_norm": 10.424148559570312,
|
| 667 |
+
"learning_rate": 0.00011936700412201653,
|
| 668 |
+
"loss": 35.1602,
|
| 669 |
+
"step": 8500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2546393965638486,
|
| 673 |
+
"grad_norm": 10.900792121887207,
|
| 674 |
+
"learning_rate": 0.00011931542906180957,
|
| 675 |
+
"loss": 34.9212,
|
| 676 |
+
"step": 8600
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2576003197797073,
|
| 680 |
+
"grad_norm": 10.541563034057617,
|
| 681 |
+
"learning_rate": 0.00011926184639471465,
|
| 682 |
+
"loss": 34.8347,
|
| 683 |
+
"step": 8700
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.26056124299556604,
|
| 687 |
+
"grad_norm": 8.576896667480469,
|
| 688 |
+
"learning_rate": 0.00011920625793430596,
|
| 689 |
+
"loss": 34.9933,
|
| 690 |
+
"step": 8800
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2635221662114247,
|
| 694 |
+
"grad_norm": 10.162493705749512,
|
| 695 |
+
"learning_rate": 0.00011914866556204637,
|
| 696 |
+
"loss": 34.3925,
|
| 697 |
+
"step": 8900
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.26648308942728344,
|
| 701 |
+
"grad_norm": 11.247607231140137,
|
| 702 |
+
"learning_rate": 0.0001190890712272237,
|
| 703 |
+
"loss": 34.4828,
|
| 704 |
+
"step": 9000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.26648308942728344,
|
| 708 |
+
"eval_loss": 4.2549567222595215,
|
| 709 |
+
"eval_runtime": 37.961,
|
| 710 |
+
"eval_samples_per_second": 28.477,
|
| 711 |
+
"eval_steps_per_second": 7.139,
|
| 712 |
+
"step": 9000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.2694440126431421,
|
| 716 |
+
"grad_norm": 9.189545631408691,
|
| 717 |
+
"learning_rate": 0.00011902747694688472,
|
| 718 |
+
"loss": 34.3655,
|
| 719 |
+
"step": 9100
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.27240493585900083,
|
| 723 |
+
"grad_norm": 11.199912071228027,
|
| 724 |
+
"learning_rate": 0.000118963884805767,
|
| 725 |
+
"loss": 34.4358,
|
| 726 |
+
"step": 9200
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.27536585907485955,
|
| 730 |
+
"grad_norm": 9.673705101013184,
|
| 731 |
+
"learning_rate": 0.00011889829695622823,
|
| 732 |
+
"loss": 34.3689,
|
| 733 |
+
"step": 9300
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.2783267822907182,
|
| 737 |
+
"grad_norm": 10.03848934173584,
|
| 738 |
+
"learning_rate": 0.00011883071561817344,
|
| 739 |
+
"loss": 33.9158,
|
| 740 |
+
"step": 9400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.28128770550657695,
|
| 744 |
+
"grad_norm": 11.581180572509766,
|
| 745 |
+
"learning_rate": 0.00011876114307897981,
|
| 746 |
+
"loss": 33.992,
|
| 747 |
+
"step": 9500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.28424862872243567,
|
| 751 |
+
"grad_norm": 10.81711483001709,
|
| 752 |
+
"learning_rate": 0.00011868958169341929,
|
| 753 |
+
"loss": 34.1195,
|
| 754 |
+
"step": 9600
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.28720955193829434,
|
| 758 |
+
"grad_norm": 9.648648262023926,
|
| 759 |
+
"learning_rate": 0.00011861603388357893,
|
| 760 |
+
"loss": 34.1664,
|
| 761 |
+
"step": 9700
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.29017047515415306,
|
| 765 |
+
"grad_norm": 11.37558364868164,
|
| 766 |
+
"learning_rate": 0.00011854050213877877,
|
| 767 |
+
"loss": 33.9937,
|
| 768 |
+
"step": 9800
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.2931313983700118,
|
| 772 |
+
"grad_norm": 9.346961975097656,
|
| 773 |
+
"learning_rate": 0.0001184629890154878,
|
| 774 |
+
"loss": 33.6917,
|
| 775 |
+
"step": 9900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.29609232158587045,
|
| 779 |
+
"grad_norm": 11.31644058227539,
|
| 780 |
+
"learning_rate": 0.0001183834971372372,
|
| 781 |
+
"loss": 33.7808,
|
| 782 |
+
"step": 10000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.29609232158587045,
|
| 786 |
+
"eval_loss": 4.157764434814453,
|
| 787 |
+
"eval_runtime": 39.9196,
|
| 788 |
+
"eval_samples_per_second": 27.079,
|
| 789 |
+
"eval_steps_per_second": 6.789,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.2990532448017292,
|
| 794 |
+
"grad_norm": 18.920991897583008,
|
| 795 |
+
"learning_rate": 0.00011180531798567065,
|
| 796 |
+
"loss": 44.0571,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.3020141680175879,
|
| 801 |
+
"grad_norm": 15.393646240234375,
|
| 802 |
+
"learning_rate": 0.0001116461207502148,
|
| 803 |
+
"loss": 39.8888,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.30497509123344657,
|
| 808 |
+
"grad_norm": 13.2774076461792,
|
| 809 |
+
"learning_rate": 0.00011148550761026972,
|
| 810 |
+
"loss": 38.6529,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.3079360144493053,
|
| 815 |
+
"grad_norm": 13.391098976135254,
|
| 816 |
+
"learning_rate": 0.00011132348296912578,
|
| 817 |
+
"loss": 37.759,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.310896937665164,
|
| 822 |
+
"grad_norm": 11.917950630187988,
|
| 823 |
+
"learning_rate": 0.00011116005126877037,
|
| 824 |
+
"loss": 37.1968,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.3138578608810227,
|
| 829 |
+
"grad_norm": 11.100213050842285,
|
| 830 |
+
"learning_rate": 0.0001109952169897661,
|
| 831 |
+
"loss": 37.213,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.3168187840968814,
|
| 836 |
+
"grad_norm": 14.579487800598145,
|
| 837 |
+
"learning_rate": 0.00011082898465112802,
|
| 838 |
+
"loss": 36.7415,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.31977970731274014,
|
| 843 |
+
"grad_norm": 11.359614372253418,
|
| 844 |
+
"learning_rate": 0.00011066135881019965,
|
| 845 |
+
"loss": 36.361,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.3227406305285988,
|
| 850 |
+
"grad_norm": 12.316486358642578,
|
| 851 |
+
"learning_rate": 0.00011049234406252809,
|
| 852 |
+
"loss": 36.0591,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.32570155374445753,
|
| 857 |
+
"grad_norm": 13.45693588256836,
|
| 858 |
+
"learning_rate": 0.00011032194504173804,
|
| 859 |
+
"loss": 35.6357,
|
| 860 |
+
"step": 11000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.32570155374445753,
|
| 864 |
+
"eval_loss": 4.41249418258667,
|
| 865 |
+
"eval_runtime": 39.8412,
|
| 866 |
+
"eval_samples_per_second": 27.133,
|
| 867 |
+
"eval_steps_per_second": 6.802,
|
| 868 |
+
"step": 11000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.32866247696031625,
|
| 872 |
+
"grad_norm": 10.018808364868164,
|
| 873 |
+
"learning_rate": 0.00011412090151135696,
|
| 874 |
+
"loss": 33.7098,
|
| 875 |
+
"step": 11100
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.3316234001761749,
|
| 879 |
+
"grad_norm": 10.30320930480957,
|
| 880 |
+
"learning_rate": 0.00011397731809339621,
|
| 881 |
+
"loss": 33.7831,
|
| 882 |
+
"step": 11200
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.33458432339203364,
|
| 886 |
+
"grad_norm": 9.650611877441406,
|
| 887 |
+
"learning_rate": 0.0001138320949911399,
|
| 888 |
+
"loss": 33.5415,
|
| 889 |
+
"step": 11300
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.33754524660789237,
|
| 893 |
+
"grad_norm": 8.77065372467041,
|
| 894 |
+
"learning_rate": 0.0001136852366160714,
|
| 895 |
+
"loss": 33.2261,
|
| 896 |
+
"step": 11400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.34050616982375104,
|
| 900 |
+
"grad_norm": 12.062385559082031,
|
| 901 |
+
"learning_rate": 0.00011353674742934919,
|
| 902 |
+
"loss": 33.0819,
|
| 903 |
+
"step": 11500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.34346709303960976,
|
| 907 |
+
"grad_norm": 10.947739601135254,
|
| 908 |
+
"learning_rate": 0.00011338663194167138,
|
| 909 |
+
"loss": 33.3451,
|
| 910 |
+
"step": 11600
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.34642801625546843,
|
| 914 |
+
"grad_norm": 9.377535820007324,
|
| 915 |
+
"learning_rate": 0.00011323489471313875,
|
| 916 |
+
"loss": 32.8928,
|
| 917 |
+
"step": 11700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.34938893947132715,
|
| 921 |
+
"grad_norm": 8.902270317077637,
|
| 922 |
+
"learning_rate": 0.00011308154035311608,
|
| 923 |
+
"loss": 33.1756,
|
| 924 |
+
"step": 11800
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.3523498626871859,
|
| 928 |
+
"grad_norm": 10.434513092041016,
|
| 929 |
+
"learning_rate": 0.00011292657352009224,
|
| 930 |
+
"loss": 33.1595,
|
| 931 |
+
"step": 11900
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.35531078590304455,
|
| 935 |
+
"grad_norm": 11.084539413452148,
|
| 936 |
+
"learning_rate": 0.00011276999892153867,
|
| 937 |
+
"loss": 33.359,
|
| 938 |
+
"step": 12000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.35531078590304455,
|
| 942 |
+
"eval_loss": 4.073917865753174,
|
| 943 |
+
"eval_runtime": 38.304,
|
| 944 |
+
"eval_samples_per_second": 28.222,
|
| 945 |
+
"eval_steps_per_second": 7.075,
|
| 946 |
+
"step": 12000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.35827170911890327,
|
| 950 |
+
"grad_norm": 7.943862438201904,
|
| 951 |
+
"learning_rate": 9.143653002276282e-05,
|
| 952 |
+
"loss": 32.5648,
|
| 953 |
+
"step": 12100
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.361232632334762,
|
| 957 |
+
"grad_norm": 8.098073959350586,
|
| 958 |
+
"learning_rate": 9.09346201340685e-05,
|
| 959 |
+
"loss": 32.1551,
|
| 960 |
+
"step": 12200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.36419355555062066,
|
| 964 |
+
"grad_norm": 7.46992826461792,
|
| 965 |
+
"learning_rate": 9.042974429385753e-05,
|
| 966 |
+
"loss": 32.3569,
|
| 967 |
+
"step": 12300
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.3671544787664794,
|
| 971 |
+
"grad_norm": 7.480947971343994,
|
| 972 |
+
"learning_rate": 8.992195090864853e-05,
|
| 973 |
+
"loss": 32.4467,
|
| 974 |
+
"step": 12400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.3701154019823381,
|
| 978 |
+
"grad_norm": 7.488786220550537,
|
| 979 |
+
"learning_rate": 8.941128866468864e-05,
|
| 980 |
+
"loss": 32.4447,
|
| 981 |
+
"step": 12500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.3730763251981968,
|
| 985 |
+
"grad_norm": 8.124217987060547,
|
| 986 |
+
"learning_rate": 8.889780652328559e-05,
|
| 987 |
+
"loss": 32.3657,
|
| 988 |
+
"step": 12600
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.3760372484140555,
|
| 992 |
+
"grad_norm": 8.322397232055664,
|
| 993 |
+
"learning_rate": 8.83815537161135e-05,
|
| 994 |
+
"loss": 31.9431,
|
| 995 |
+
"step": 12700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.3789981716299142,
|
| 999 |
+
"grad_norm": 8.59915828704834,
|
| 1000 |
+
"learning_rate": 8.786257974049245e-05,
|
| 1001 |
+
"loss": 31.9211,
|
| 1002 |
+
"step": 12800
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.3819590948457729,
|
| 1006 |
+
"grad_norm": 8.048558235168457,
|
| 1007 |
+
"learning_rate": 8.734093435464301e-05,
|
| 1008 |
+
"loss": 32.437,
|
| 1009 |
+
"step": 12900
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.3849200180616316,
|
| 1013 |
+
"grad_norm": 7.816276550292969,
|
| 1014 |
+
"learning_rate": 8.681666757291531e-05,
|
| 1015 |
+
"loss": 32.0396,
|
| 1016 |
+
"step": 13000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.3849200180616316,
|
| 1020 |
+
"eval_loss": 3.9447479248046875,
|
| 1021 |
+
"eval_runtime": 112.3499,
|
| 1022 |
+
"eval_samples_per_second": 9.622,
|
| 1023 |
+
"eval_steps_per_second": 2.412,
|
| 1024 |
+
"step": 13000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.38788094127749034,
|
| 1028 |
+
"grad_norm": 8.613288879394531,
|
| 1029 |
+
"learning_rate": 8.628982966099388e-05,
|
| 1030 |
+
"loss": 31.874,
|
| 1031 |
+
"step": 13100
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.390841864493349,
|
| 1035 |
+
"grad_norm": 7.478573799133301,
|
| 1036 |
+
"learning_rate": 8.576047113107821e-05,
|
| 1037 |
+
"loss": 31.7233,
|
| 1038 |
+
"step": 13200
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.39380278770920774,
|
| 1042 |
+
"grad_norm": 7.845474720001221,
|
| 1043 |
+
"learning_rate": 8.52286427370398e-05,
|
| 1044 |
+
"loss": 31.628,
|
| 1045 |
+
"step": 13300
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39676371092506646,
|
| 1049 |
+
"grad_norm": 7.7132158279418945,
|
| 1050 |
+
"learning_rate": 8.469439546955592e-05,
|
| 1051 |
+
"loss": 31.8516,
|
| 1052 |
+
"step": 13400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.39972463414092513,
|
| 1056 |
+
"grad_norm": 9.245190620422363,
|
| 1057 |
+
"learning_rate": 8.415778055122073e-05,
|
| 1058 |
+
"loss": 31.8406,
|
| 1059 |
+
"step": 13500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.40268555735678385,
|
| 1063 |
+
"grad_norm": 8.426488876342773,
|
| 1064 |
+
"learning_rate": 8.361884943163423e-05,
|
| 1065 |
+
"loss": 31.7148,
|
| 1066 |
+
"step": 13600
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4056464805726426,
|
| 1070 |
+
"grad_norm": 7.879675388336182,
|
| 1071 |
+
"learning_rate": 8.307765378246925e-05,
|
| 1072 |
+
"loss": 31.9798,
|
| 1073 |
+
"step": 13700
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.40860740378850124,
|
| 1077 |
+
"grad_norm": 8.469719886779785,
|
| 1078 |
+
"learning_rate": 8.253424549251735e-05,
|
| 1079 |
+
"loss": 31.6741,
|
| 1080 |
+
"step": 13800
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.41156832700435997,
|
| 1084 |
+
"grad_norm": 8.198810577392578,
|
| 1085 |
+
"learning_rate": 8.198867666271385e-05,
|
| 1086 |
+
"loss": 31.6722,
|
| 1087 |
+
"step": 13900
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41452925022021864,
|
| 1091 |
+
"grad_norm": 7.881684303283691,
|
| 1092 |
+
"learning_rate": 8.144099960114239e-05,
|
| 1093 |
+
"loss": 31.8682,
|
| 1094 |
+
"step": 14000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.41452925022021864,
|
| 1098 |
+
"eval_loss": 3.904888153076172,
|
| 1099 |
+
"eval_runtime": 110.4703,
|
| 1100 |
+
"eval_samples_per_second": 9.785,
|
| 1101 |
+
"eval_steps_per_second": 2.453,
|
| 1102 |
+
"step": 14000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.41749017343607736,
|
| 1106 |
+
"grad_norm": 7.772391319274902,
|
| 1107 |
+
"learning_rate": 8.089126681801981e-05,
|
| 1108 |
+
"loss": 32.0349,
|
| 1109 |
+
"step": 14100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.4204510966519361,
|
| 1113 |
+
"grad_norm": 8.459504127502441,
|
| 1114 |
+
"learning_rate": 8.033953102066161e-05,
|
| 1115 |
+
"loss": 31.5844,
|
| 1116 |
+
"step": 14200
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.42341201986779475,
|
| 1120 |
+
"grad_norm": 7.765544414520264,
|
| 1121 |
+
"learning_rate": 7.978584510842833e-05,
|
| 1122 |
+
"loss": 31.6879,
|
| 1123 |
+
"step": 14300
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.4263729430836535,
|
| 1127 |
+
"grad_norm": 8.06749153137207,
|
| 1128 |
+
"learning_rate": 7.923026216765381e-05,
|
| 1129 |
+
"loss": 31.5893,
|
| 1130 |
+
"step": 14400
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.4293338662995122,
|
| 1134 |
+
"grad_norm": 8.966425895690918,
|
| 1135 |
+
"learning_rate": 7.86728354665553e-05,
|
| 1136 |
+
"loss": 31.392,
|
| 1137 |
+
"step": 14500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.43229478951537087,
|
| 1141 |
+
"grad_norm": 8.47319221496582,
|
| 1142 |
+
"learning_rate": 7.81136184501262e-05,
|
| 1143 |
+
"loss": 31.3068,
|
| 1144 |
+
"step": 14600
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.4352557127312296,
|
| 1148 |
+
"grad_norm": 8.642230033874512,
|
| 1149 |
+
"learning_rate": 7.755266473501193e-05,
|
| 1150 |
+
"loss": 31.5877,
|
| 1151 |
+
"step": 14700
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.4382166359470883,
|
| 1155 |
+
"grad_norm": 8.412428855895996,
|
| 1156 |
+
"learning_rate": 7.699002810436915e-05,
|
| 1157 |
+
"loss": 31.6239,
|
| 1158 |
+
"step": 14800
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.441177559162947,
|
| 1162 |
+
"grad_norm": 6.971558094024658,
|
| 1163 |
+
"learning_rate": 7.642576250270929e-05,
|
| 1164 |
+
"loss": 31.7946,
|
| 1165 |
+
"step": 14900
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.4441384823788057,
|
| 1169 |
+
"grad_norm": 7.922480583190918,
|
| 1170 |
+
"learning_rate": 7.585992203072628e-05,
|
| 1171 |
+
"loss": 31.4474,
|
| 1172 |
+
"step": 15000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.4441384823788057,
|
| 1176 |
+
"eval_loss": 3.875948667526245,
|
| 1177 |
+
"eval_runtime": 109.3049,
|
| 1178 |
+
"eval_samples_per_second": 9.89,
|
| 1179 |
+
"eval_steps_per_second": 2.479,
|
| 1180 |
+
"step": 15000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.44709940559466443,
|
| 1184 |
+
"grad_norm": 8.747485160827637,
|
| 1185 |
+
"learning_rate": 7.529256094010965e-05,
|
| 1186 |
+
"loss": 31.6016,
|
| 1187 |
+
"step": 15100
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.4500603288105231,
|
| 1191 |
+
"grad_norm": 8.723346710205078,
|
| 1192 |
+
"learning_rate": 7.472373362834283e-05,
|
| 1193 |
+
"loss": 31.2744,
|
| 1194 |
+
"step": 15200
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.4530212520263818,
|
| 1198 |
+
"grad_norm": 8.310611724853516,
|
| 1199 |
+
"learning_rate": 7.415349463348775e-05,
|
| 1200 |
+
"loss": 31.7448,
|
| 1201 |
+
"step": 15300
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.45598217524224055,
|
| 1205 |
+
"grad_norm": 8.236388206481934,
|
| 1206 |
+
"learning_rate": 7.358189862895577e-05,
|
| 1207 |
+
"loss": 30.9859,
|
| 1208 |
+
"step": 15400
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.4589430984580992,
|
| 1212 |
+
"grad_norm": 8.104386329650879,
|
| 1213 |
+
"learning_rate": 7.300900041826566e-05,
|
| 1214 |
+
"loss": 31.1935,
|
| 1215 |
+
"step": 15500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.46190402167395794,
|
| 1219 |
+
"grad_norm": 8.219923973083496,
|
| 1220 |
+
"learning_rate": 7.243485492978928e-05,
|
| 1221 |
+
"loss": 30.9099,
|
| 1222 |
+
"step": 15600
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.46486494488981667,
|
| 1226 |
+
"grad_norm": 8.872945785522461,
|
| 1227 |
+
"learning_rate": 7.185951721148502e-05,
|
| 1228 |
+
"loss": 31.3423,
|
| 1229 |
+
"step": 15700
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.46782586810567534,
|
| 1233 |
+
"grad_norm": 8.087647438049316,
|
| 1234 |
+
"learning_rate": 7.128304242561999e-05,
|
| 1235 |
+
"loss": 31.1816,
|
| 1236 |
+
"step": 15800
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.47078679132153406,
|
| 1240 |
+
"grad_norm": 8.805392265319824,
|
| 1241 |
+
"learning_rate": 7.070548584348108e-05,
|
| 1242 |
+
"loss": 31.0977,
|
| 1243 |
+
"step": 15900
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.4737477145373928,
|
| 1247 |
+
"grad_norm": 8.469452857971191,
|
| 1248 |
+
"learning_rate": 7.012690284007577e-05,
|
| 1249 |
+
"loss": 31.5828,
|
| 1250 |
+
"step": 16000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.4737477145373928,
|
| 1254 |
+
"eval_loss": 3.8530030250549316,
|
| 1255 |
+
"eval_runtime": 109.275,
|
| 1256 |
+
"eval_samples_per_second": 9.892,
|
| 1257 |
+
"eval_steps_per_second": 2.48,
|
| 1258 |
+
"step": 16000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.47670863775325145,
|
| 1262 |
+
"grad_norm": 8.871159553527832,
|
| 1263 |
+
"learning_rate": 6.954734888882281e-05,
|
| 1264 |
+
"loss": 30.9753,
|
| 1265 |
+
"step": 16100
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.4796695609691102,
|
| 1269 |
+
"grad_norm": 8.81116008758545,
|
| 1270 |
+
"learning_rate": 6.896687955623357e-05,
|
| 1271 |
+
"loss": 31.2067,
|
| 1272 |
+
"step": 16200
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.4826304841849689,
|
| 1276 |
+
"grad_norm": 7.77982759475708,
|
| 1277 |
+
"learning_rate": 6.838555049658432e-05,
|
| 1278 |
+
"loss": 31.089,
|
| 1279 |
+
"step": 16300
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.48559140740082757,
|
| 1283 |
+
"grad_norm": 8.370245933532715,
|
| 1284 |
+
"learning_rate": 6.780341744658044e-05,
|
| 1285 |
+
"loss": 30.9776,
|
| 1286 |
+
"step": 16400
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.4885523306166863,
|
| 1290 |
+
"grad_norm": 8.41613483428955,
|
| 1291 |
+
"learning_rate": 6.722053622001221e-05,
|
| 1292 |
+
"loss": 31.1095,
|
| 1293 |
+
"step": 16500
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.49151325383254496,
|
| 1297 |
+
"grad_norm": 7.951696395874023,
|
| 1298 |
+
"learning_rate": 6.663696270240373e-05,
|
| 1299 |
+
"loss": 31.1532,
|
| 1300 |
+
"step": 16600
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.4944741770484037,
|
| 1304 |
+
"grad_norm": 9.02717113494873,
|
| 1305 |
+
"learning_rate": 6.60527528456546e-05,
|
| 1306 |
+
"loss": 31.0777,
|
| 1307 |
+
"step": 16700
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.4974351002642624,
|
| 1311 |
+
"grad_norm": 8.57259750366211,
|
| 1312 |
+
"learning_rate": 6.546796266267535e-05,
|
| 1313 |
+
"loss": 31.3509,
|
| 1314 |
+
"step": 16800
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.5003960234801211,
|
| 1318 |
+
"grad_norm": 9.129491806030273,
|
| 1319 |
+
"learning_rate": 6.488264822201711e-05,
|
| 1320 |
+
"loss": 30.7844,
|
| 1321 |
+
"step": 16900
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.5033569466959799,
|
| 1325 |
+
"grad_norm": 8.600064277648926,
|
| 1326 |
+
"learning_rate": 6.429686564249579e-05,
|
| 1327 |
+
"loss": 31.1164,
|
| 1328 |
+
"step": 17000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.5033569466959799,
|
| 1332 |
+
"eval_loss": 3.836409091949463,
|
| 1333 |
+
"eval_runtime": 109.0903,
|
| 1334 |
+
"eval_samples_per_second": 9.909,
|
| 1335 |
+
"eval_steps_per_second": 2.484,
|
| 1336 |
+
"step": 17000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5063178699118385,
|
| 1340 |
+
"grad_norm": 8.62096881866455,
|
| 1341 |
+
"learning_rate": 6.371067108781158e-05,
|
| 1342 |
+
"loss": 31.1944,
|
| 1343 |
+
"step": 17100
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5092787931276972,
|
| 1347 |
+
"grad_norm": 8.052851676940918,
|
| 1348 |
+
"learning_rate": 6.312412076116401e-05,
|
| 1349 |
+
"loss": 31.0126,
|
| 1350 |
+
"step": 17200
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5122397163435559,
|
| 1354 |
+
"grad_norm": 8.32268238067627,
|
| 1355 |
+
"learning_rate": 6.253727089986337e-05,
|
| 1356 |
+
"loss": 31.0692,
|
| 1357 |
+
"step": 17300
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5152006395594146,
|
| 1361 |
+
"grad_norm": 8.130902290344238,
|
| 1362 |
+
"learning_rate": 6.195017776993876e-05,
|
| 1363 |
+
"loss": 30.9143,
|
| 1364 |
+
"step": 17400
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.5181615627752734,
|
| 1368 |
+
"grad_norm": 9.245232582092285,
|
| 1369 |
+
"learning_rate": 6.136289766074334e-05,
|
| 1370 |
+
"loss": 31.0029,
|
| 1371 |
+
"step": 17500
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5211224859911321,
|
| 1375 |
+
"grad_norm": 8.296626091003418,
|
| 1376 |
+
"learning_rate": 6.077548687955759e-05,
|
| 1377 |
+
"loss": 31.0624,
|
| 1378 |
+
"step": 17600
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5240834092069907,
|
| 1382 |
+
"grad_norm": 8.933104515075684,
|
| 1383 |
+
"learning_rate": 6.018800174619048e-05,
|
| 1384 |
+
"loss": 31.0619,
|
| 1385 |
+
"step": 17700
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5270443324228494,
|
| 1389 |
+
"grad_norm": 7.37945032119751,
|
| 1390 |
+
"learning_rate": 5.960049858757974e-05,
|
| 1391 |
+
"loss": 31.3181,
|
| 1392 |
+
"step": 17800
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5300052556387082,
|
| 1396 |
+
"grad_norm": 8.817550659179688,
|
| 1397 |
+
"learning_rate": 5.901303373239133e-05,
|
| 1398 |
+
"loss": 30.8424,
|
| 1399 |
+
"step": 17900
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5329661788545669,
|
| 1403 |
+
"grad_norm": 7.71854305267334,
|
| 1404 |
+
"learning_rate": 5.842566350561879e-05,
|
| 1405 |
+
"loss": 31.0376,
|
| 1406 |
+
"step": 18000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5329661788545669,
|
| 1410 |
+
"eval_loss": 3.822613477706909,
|
| 1411 |
+
"eval_runtime": 112.0979,
|
| 1412 |
+
"eval_samples_per_second": 9.643,
|
| 1413 |
+
"eval_steps_per_second": 2.418,
|
| 1414 |
+
"step": 18000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.5359271020704256,
|
| 1418 |
+
"grad_norm": 8.84870719909668,
|
| 1419 |
+
"learning_rate": 5.7838444223182826e-05,
|
| 1420 |
+
"loss": 30.8901,
|
| 1421 |
+
"step": 18100
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.5388880252862842,
|
| 1425 |
+
"grad_norm": 7.48129415512085,
|
| 1426 |
+
"learning_rate": 5.725143218653187e-05,
|
| 1427 |
+
"loss": 31.0275,
|
| 1428 |
+
"step": 18200
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.5418489485021429,
|
| 1432 |
+
"grad_norm": 8.218484878540039,
|
| 1433 |
+
"learning_rate": 5.666468367724412e-05,
|
| 1434 |
+
"loss": 31.1443,
|
| 1435 |
+
"step": 18300
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.5448098717180017,
|
| 1439 |
+
"grad_norm": 9.589841842651367,
|
| 1440 |
+
"learning_rate": 5.607825495163119e-05,
|
| 1441 |
+
"loss": 30.9756,
|
| 1442 |
+
"step": 18400
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.5477707949338604,
|
| 1446 |
+
"grad_norm": 8.583683013916016,
|
| 1447 |
+
"learning_rate": 5.549220223534451e-05,
|
| 1448 |
+
"loss": 31.0641,
|
| 1449 |
+
"step": 18500
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.5507317181497191,
|
| 1453 |
+
"grad_norm": 7.978188991546631,
|
| 1454 |
+
"learning_rate": 5.490658171798439e-05,
|
| 1455 |
+
"loss": 30.8899,
|
| 1456 |
+
"step": 18600
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.5536926413655778,
|
| 1460 |
+
"grad_norm": 8.130802154541016,
|
| 1461 |
+
"learning_rate": 5.432144954771287e-05,
|
| 1462 |
+
"loss": 31.0812,
|
| 1463 |
+
"step": 18700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.5566535645814364,
|
| 1467 |
+
"grad_norm": 8.981709480285645,
|
| 1468 |
+
"learning_rate": 5.37368618258701e-05,
|
| 1469 |
+
"loss": 31.0612,
|
| 1470 |
+
"step": 18800
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.5596144877972952,
|
| 1474 |
+
"grad_norm": 7.87661075592041,
|
| 1475 |
+
"learning_rate": 5.315287460159561e-05,
|
| 1476 |
+
"loss": 30.8581,
|
| 1477 |
+
"step": 18900
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.5625754110131539,
|
| 1481 |
+
"grad_norm": 8.329483032226562,
|
| 1482 |
+
"learning_rate": 5.256954386645438e-05,
|
| 1483 |
+
"loss": 31.1805,
|
| 1484 |
+
"step": 19000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.5625754110131539,
|
| 1488 |
+
"eval_loss": 3.8131661415100098,
|
| 1489 |
+
"eval_runtime": 111.5683,
|
| 1490 |
+
"eval_samples_per_second": 9.689,
|
| 1491 |
+
"eval_steps_per_second": 2.429,
|
| 1492 |
+
"step": 19000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.5655363342290126,
|
| 1496 |
+
"grad_norm": 8.833015441894531,
|
| 1497 |
+
"learning_rate": 5.198692554906851e-05,
|
| 1498 |
+
"loss": 30.9231,
|
| 1499 |
+
"step": 19100
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.5684972574448713,
|
| 1503 |
+
"grad_norm": 7.966989994049072,
|
| 1504 |
+
"learning_rate": 5.1405075509754834e-05,
|
| 1505 |
+
"loss": 31.0225,
|
| 1506 |
+
"step": 19200
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.5714581806607301,
|
| 1510 |
+
"grad_norm": 8.791169166564941,
|
| 1511 |
+
"learning_rate": 5.0824049535169166e-05,
|
| 1512 |
+
"loss": 31.1551,
|
| 1513 |
+
"step": 19300
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.5744191038765887,
|
| 1517 |
+
"grad_norm": 7.9680023193359375,
|
| 1518 |
+
"learning_rate": 5.024390333295761e-05,
|
| 1519 |
+
"loss": 31.0498,
|
| 1520 |
+
"step": 19400
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.5773800270924474,
|
| 1524 |
+
"grad_norm": 8.603718757629395,
|
| 1525 |
+
"learning_rate": 4.966469252641538e-05,
|
| 1526 |
+
"loss": 30.9017,
|
| 1527 |
+
"step": 19500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.5803409503083061,
|
| 1531 |
+
"grad_norm": 12.401627540588379,
|
| 1532 |
+
"learning_rate": 4.908647264915378e-05,
|
| 1533 |
+
"loss": 30.9988,
|
| 1534 |
+
"step": 19600
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.5833018735241648,
|
| 1538 |
+
"grad_norm": 8.433266639709473,
|
| 1539 |
+
"learning_rate": 4.8509299139775734e-05,
|
| 1540 |
+
"loss": 30.9905,
|
| 1541 |
+
"step": 19700
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.5862627967400236,
|
| 1545 |
+
"grad_norm": 7.99282693862915,
|
| 1546 |
+
"learning_rate": 4.7933227336560414e-05,
|
| 1547 |
+
"loss": 31.0604,
|
| 1548 |
+
"step": 19800
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.5892237199558823,
|
| 1552 |
+
"grad_norm": 8.011063575744629,
|
| 1553 |
+
"learning_rate": 4.735831247215753e-05,
|
| 1554 |
+
"loss": 30.7471,
|
| 1555 |
+
"step": 19900
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.5921846431717409,
|
| 1559 |
+
"grad_norm": 9.603862762451172,
|
| 1560 |
+
"learning_rate": 4.67846096682918e-05,
|
| 1561 |
+
"loss": 30.8428,
|
| 1562 |
+
"step": 20000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.5921846431717409,
|
| 1566 |
+
"eval_loss": 3.8060901165008545,
|
| 1567 |
+
"eval_runtime": 112.6154,
|
| 1568 |
+
"eval_samples_per_second": 9.599,
|
| 1569 |
+
"eval_steps_per_second": 2.406,
|
| 1570 |
+
"step": 20000
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5951455663875996,
|
| 1574 |
+
"grad_norm": 8.427188873291016,
|
| 1575 |
+
"learning_rate": 4.6212173930477874e-05,
|
| 1576 |
+
"loss": 30.8438,
|
| 1577 |
+
"step": 20100
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5981064896034584,
|
| 1581 |
+
"grad_norm": 7.692320346832275,
|
| 1582 |
+
"learning_rate": 4.5641060142746556e-05,
|
| 1583 |
+
"loss": 30.7664,
|
| 1584 |
+
"step": 20200
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.6010674128193171,
|
| 1588 |
+
"grad_norm": 8.596179962158203,
|
| 1589 |
+
"learning_rate": 4.507132306238262e-05,
|
| 1590 |
+
"loss": 30.9387,
|
| 1591 |
+
"step": 20300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6040283360351758,
|
| 1595 |
+
"grad_norm": 8.076534271240234,
|
| 1596 |
+
"learning_rate": 4.450301731467488e-05,
|
| 1597 |
+
"loss": 30.851,
|
| 1598 |
+
"step": 20400
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6069892592510344,
|
| 1602 |
+
"grad_norm": 9.05728816986084,
|
| 1603 |
+
"learning_rate": 4.3936197387678665e-05,
|
| 1604 |
+
"loss": 30.7486,
|
| 1605 |
+
"step": 20500
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6099501824668931,
|
| 1609 |
+
"grad_norm": 8.477595329284668,
|
| 1610 |
+
"learning_rate": 4.3370917626991706e-05,
|
| 1611 |
+
"loss": 30.6843,
|
| 1612 |
+
"step": 20600
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.6129111056827519,
|
| 1616 |
+
"grad_norm": 8.171915054321289,
|
| 1617 |
+
"learning_rate": 4.2807232230543625e-05,
|
| 1618 |
+
"loss": 30.9551,
|
| 1619 |
+
"step": 20700
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6158720288986106,
|
| 1623 |
+
"grad_norm": 8.333806991577148,
|
| 1624 |
+
"learning_rate": 4.22451952433994e-05,
|
| 1625 |
+
"loss": 30.8566,
|
| 1626 |
+
"step": 20800
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6188329521144693,
|
| 1630 |
+
"grad_norm": 7.9477715492248535,
|
| 1631 |
+
"learning_rate": 4.168486055257777e-05,
|
| 1632 |
+
"loss": 30.8577,
|
| 1633 |
+
"step": 20900
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.621793875330328,
|
| 1637 |
+
"grad_norm": 8.560218811035156,
|
| 1638 |
+
"learning_rate": 4.112628188188457e-05,
|
| 1639 |
+
"loss": 30.7203,
|
| 1640 |
+
"step": 21000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.621793875330328,
|
| 1644 |
+
"eval_loss": 3.7986109256744385,
|
| 1645 |
+
"eval_runtime": 109.4771,
|
| 1646 |
+
"eval_samples_per_second": 9.874,
|
| 1647 |
+
"eval_steps_per_second": 2.475,
|
| 1648 |
+
"step": 21000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.6247547985461867,
|
| 1652 |
+
"grad_norm": 8.963776588439941,
|
| 1653 |
+
"learning_rate": 4.056951278676187e-05,
|
| 1654 |
+
"loss": 30.9418,
|
| 1655 |
+
"step": 21100
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.6277157217620454,
|
| 1659 |
+
"grad_norm": 8.338837623596191,
|
| 1660 |
+
"learning_rate": 4.001460664915308e-05,
|
| 1661 |
+
"loss": 30.756,
|
| 1662 |
+
"step": 21200
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.6306766449779041,
|
| 1666 |
+
"grad_norm": 8.323155403137207,
|
| 1667 |
+
"learning_rate": 3.946161667238485e-05,
|
| 1668 |
+
"loss": 30.6959,
|
| 1669 |
+
"step": 21300
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.6336375681937628,
|
| 1673 |
+
"grad_norm": 9.881996154785156,
|
| 1674 |
+
"learning_rate": 3.8910595876066085e-05,
|
| 1675 |
+
"loss": 30.9333,
|
| 1676 |
+
"step": 21400
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.6365984914096215,
|
| 1680 |
+
"grad_norm": 8.089996337890625,
|
| 1681 |
+
"learning_rate": 3.836159709100446e-05,
|
| 1682 |
+
"loss": 30.6899,
|
| 1683 |
+
"step": 21500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.6395594146254803,
|
| 1687 |
+
"grad_norm": 7.9427289962768555,
|
| 1688 |
+
"learning_rate": 3.7814672954141055e-05,
|
| 1689 |
+
"loss": 30.8046,
|
| 1690 |
+
"step": 21600
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.6425203378413389,
|
| 1694 |
+
"grad_norm": 8.468146324157715,
|
| 1695 |
+
"learning_rate": 3.7269875903503826e-05,
|
| 1696 |
+
"loss": 31.2292,
|
| 1697 |
+
"step": 21700
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.6454812610571976,
|
| 1701 |
+
"grad_norm": 8.63842487335205,
|
| 1702 |
+
"learning_rate": 3.672725817317973e-05,
|
| 1703 |
+
"loss": 30.7721,
|
| 1704 |
+
"step": 21800
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.6484421842730563,
|
| 1708 |
+
"grad_norm": 8.145241737365723,
|
| 1709 |
+
"learning_rate": 3.6186871788306674e-05,
|
| 1710 |
+
"loss": 30.5881,
|
| 1711 |
+
"step": 21900
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.6514031074889151,
|
| 1715 |
+
"grad_norm": 8.194993019104004,
|
| 1716 |
+
"learning_rate": 3.5648768560085604e-05,
|
| 1717 |
+
"loss": 30.9425,
|
| 1718 |
+
"step": 22000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.6514031074889151,
|
| 1722 |
+
"eval_loss": 3.7950870990753174,
|
| 1723 |
+
"eval_runtime": 109.4264,
|
| 1724 |
+
"eval_samples_per_second": 9.879,
|
| 1725 |
+
"eval_steps_per_second": 2.477,
|
| 1726 |
+
"step": 22000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.6543640307047738,
|
| 1730 |
+
"grad_norm": 9.304323196411133,
|
| 1731 |
+
"learning_rate": 3.511300008081273e-05,
|
| 1732 |
+
"loss": 30.722,
|
| 1733 |
+
"step": 22100
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.6573249539206325,
|
| 1737 |
+
"grad_norm": 7.82930850982666,
|
| 1738 |
+
"learning_rate": 3.4579617718933054e-05,
|
| 1739 |
+
"loss": 30.7943,
|
| 1740 |
+
"step": 22200
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.6602858771364911,
|
| 1744 |
+
"grad_norm": 7.912548542022705,
|
| 1745 |
+
"learning_rate": 3.4048672614115294e-05,
|
| 1746 |
+
"loss": 30.8451,
|
| 1747 |
+
"step": 22300
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.6632468003523498,
|
| 1751 |
+
"grad_norm": 8.46181583404541,
|
| 1752 |
+
"learning_rate": 3.352021567234869e-05,
|
| 1753 |
+
"loss": 30.9009,
|
| 1754 |
+
"step": 22400
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.6662077235682086,
|
| 1758 |
+
"grad_norm": 7.727646827697754,
|
| 1759 |
+
"learning_rate": 3.299429756106215e-05,
|
| 1760 |
+
"loss": 30.8281,
|
| 1761 |
+
"step": 22500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.6691686467840673,
|
| 1765 |
+
"grad_norm": 8.119136810302734,
|
| 1766 |
+
"learning_rate": 3.247096870426649e-05,
|
| 1767 |
+
"loss": 30.7757,
|
| 1768 |
+
"step": 22600
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.672129569999926,
|
| 1772 |
+
"grad_norm": 8.091607093811035,
|
| 1773 |
+
"learning_rate": 3.195027927771982e-05,
|
| 1774 |
+
"loss": 30.8661,
|
| 1775 |
+
"step": 22700
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.6750904932157847,
|
| 1779 |
+
"grad_norm": 7.598474979400635,
|
| 1780 |
+
"learning_rate": 3.1432279204116776e-05,
|
| 1781 |
+
"loss": 30.6257,
|
| 1782 |
+
"step": 22800
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.6780514164316434,
|
| 1786 |
+
"grad_norm": 9.547100067138672,
|
| 1787 |
+
"learning_rate": 3.091701814830198e-05,
|
| 1788 |
+
"loss": 30.8582,
|
| 1789 |
+
"step": 22900
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.6810123396475021,
|
| 1793 |
+
"grad_norm": 7.637078762054443,
|
| 1794 |
+
"learning_rate": 3.0404545512508415e-05,
|
| 1795 |
+
"loss": 30.9432,
|
| 1796 |
+
"step": 23000
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.6810123396475021,
|
| 1800 |
+
"eval_loss": 3.791748285293579,
|
| 1801 |
+
"eval_runtime": 109.2867,
|
| 1802 |
+
"eval_samples_per_second": 9.891,
|
| 1803 |
+
"eval_steps_per_second": 2.48,
|
| 1804 |
+
"step": 23000
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 0.6839732628633608,
|
| 1808 |
+
"grad_norm": 8.485209465026855,
|
| 1809 |
+
"learning_rate": 2.98949104316207e-05,
|
| 1810 |
+
"loss": 30.921,
|
| 1811 |
+
"step": 23100
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 0.6869341860792195,
|
| 1815 |
+
"grad_norm": 7.777042865753174,
|
| 1816 |
+
"learning_rate": 2.938816176846421e-05,
|
| 1817 |
+
"loss": 30.8116,
|
| 1818 |
+
"step": 23200
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.6898951092950782,
|
| 1822 |
+
"grad_norm": 7.6587138175964355,
|
| 1823 |
+
"learning_rate": 2.8884348109120106e-05,
|
| 1824 |
+
"loss": 30.7965,
|
| 1825 |
+
"step": 23300
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 0.6928560325109369,
|
| 1829 |
+
"grad_norm": 8.276775360107422,
|
| 1830 |
+
"learning_rate": 2.8383517758267178e-05,
|
| 1831 |
+
"loss": 30.6582,
|
| 1832 |
+
"step": 23400
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 0.6958169557267956,
|
| 1836 |
+
"grad_norm": 7.5494771003723145,
|
| 1837 |
+
"learning_rate": 2.7885718734550257e-05,
|
| 1838 |
+
"loss": 30.6483,
|
| 1839 |
+
"step": 23500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.6987778789426543,
|
| 1843 |
+
"grad_norm": 7.938130855560303,
|
| 1844 |
+
"learning_rate": 2.739099876597646e-05,
|
| 1845 |
+
"loss": 30.529,
|
| 1846 |
+
"step": 23600
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.701738802158513,
|
| 1850 |
+
"grad_norm": 8.202885627746582,
|
| 1851 |
+
"learning_rate": 2.6899405285339026e-05,
|
| 1852 |
+
"loss": 30.825,
|
| 1853 |
+
"step": 23700
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 0.7046997253743718,
|
| 1857 |
+
"grad_norm": 8.393240928649902,
|
| 1858 |
+
"learning_rate": 2.6410985425669622e-05,
|
| 1859 |
+
"loss": 30.7867,
|
| 1860 |
+
"step": 23800
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 0.7076606485902305,
|
| 1864 |
+
"grad_norm": 8.32459831237793,
|
| 1865 |
+
"learning_rate": 2.5925786015719207e-05,
|
| 1866 |
+
"loss": 30.7898,
|
| 1867 |
+
"step": 23900
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 0.7106215718060891,
|
| 1871 |
+
"grad_norm": 9.323598861694336,
|
| 1872 |
+
"learning_rate": 2.544385357546831e-05,
|
| 1873 |
+
"loss": 30.5684,
|
| 1874 |
+
"step": 24000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.7106215718060891,
|
| 1878 |
+
"eval_loss": 3.789947271347046,
|
| 1879 |
+
"eval_runtime": 110.7686,
|
| 1880 |
+
"eval_samples_per_second": 9.759,
|
| 1881 |
+
"eval_steps_per_second": 2.447,
|
| 1882 |
+
"step": 24000
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.7135824950219478,
|
| 1886 |
+
"grad_norm": 8.184738159179688,
|
| 1887 |
+
"learning_rate": 2.4965234311666717e-05,
|
| 1888 |
+
"loss": 30.7187,
|
| 1889 |
+
"step": 24100
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.7165434182378065,
|
| 1893 |
+
"grad_norm": 7.82784366607666,
|
| 1894 |
+
"learning_rate": 2.4489974113403275e-05,
|
| 1895 |
+
"loss": 30.705,
|
| 1896 |
+
"step": 24200
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.7195043414536653,
|
| 1900 |
+
"grad_norm": 7.945186614990234,
|
| 1901 |
+
"learning_rate": 2.4018118547706078e-05,
|
| 1902 |
+
"loss": 30.4846,
|
| 1903 |
+
"step": 24300
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.722465264669524,
|
| 1907 |
+
"grad_norm": 9.277371406555176,
|
| 1908 |
+
"learning_rate": 2.3549712855173688e-05,
|
| 1909 |
+
"loss": 30.6765,
|
| 1910 |
+
"step": 24400
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.7254261878853827,
|
| 1914 |
+
"grad_norm": 8.619938850402832,
|
| 1915 |
+
"learning_rate": 2.3084801945637512e-05,
|
| 1916 |
+
"loss": 30.6503,
|
| 1917 |
+
"step": 24500
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.7283871111012413,
|
| 1921 |
+
"grad_norm": 8.467925071716309,
|
| 1922 |
+
"learning_rate": 2.262343039385585e-05,
|
| 1923 |
+
"loss": 30.957,
|
| 1924 |
+
"step": 24600
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.7313480343171,
|
| 1928 |
+
"grad_norm": 8.035057067871094,
|
| 1929 |
+
"learning_rate": 2.216564243524035e-05,
|
| 1930 |
+
"loss": 30.6764,
|
| 1931 |
+
"step": 24700
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.7343089575329588,
|
| 1935 |
+
"grad_norm": 7.555221080780029,
|
| 1936 |
+
"learning_rate": 2.1711481961614565e-05,
|
| 1937 |
+
"loss": 30.7666,
|
| 1938 |
+
"step": 24800
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.7372698807488175,
|
| 1942 |
+
"grad_norm": 7.959348201751709,
|
| 1943 |
+
"learning_rate": 2.1260992517005892e-05,
|
| 1944 |
+
"loss": 30.8212,
|
| 1945 |
+
"step": 24900
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.7402308039646762,
|
| 1949 |
+
"grad_norm": 7.882981300354004,
|
| 1950 |
+
"learning_rate": 2.0814217293470476e-05,
|
| 1951 |
+
"loss": 30.8312,
|
| 1952 |
+
"step": 25000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.7402308039646762,
|
| 1956 |
+
"eval_loss": 3.7874350547790527,
|
| 1957 |
+
"eval_runtime": 107.8316,
|
| 1958 |
+
"eval_samples_per_second": 10.025,
|
| 1959 |
+
"eval_steps_per_second": 2.513,
|
| 1960 |
+
"step": 25000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.743191727180535,
|
| 1964 |
+
"grad_norm": 7.499105930328369,
|
| 1965 |
+
"learning_rate": 2.0371199126952268e-05,
|
| 1966 |
+
"loss": 30.9958,
|
| 1967 |
+
"step": 25100
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.7461526503963936,
|
| 1971 |
+
"grad_norm": 7.973631381988525,
|
| 1972 |
+
"learning_rate": 1.9931980493175735e-05,
|
| 1973 |
+
"loss": 30.6469,
|
| 1974 |
+
"step": 25200
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.7491135736122523,
|
| 1978 |
+
"grad_norm": 7.996872425079346,
|
| 1979 |
+
"learning_rate": 1.949660350357356e-05,
|
| 1980 |
+
"loss": 30.6363,
|
| 1981 |
+
"step": 25300
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.752074496828111,
|
| 1985 |
+
"grad_norm": 8.139349937438965,
|
| 1986 |
+
"learning_rate": 1.9065109901249e-05,
|
| 1987 |
+
"loss": 30.924,
|
| 1988 |
+
"step": 25400
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.7550354200439697,
|
| 1992 |
+
"grad_norm": 8.981887817382812,
|
| 1993 |
+
"learning_rate": 1.863754105697369e-05,
|
| 1994 |
+
"loss": 30.9555,
|
| 1995 |
+
"step": 25500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 0.7579963432598285,
|
| 1999 |
+
"grad_norm": 7.660996913909912,
|
| 2000 |
+
"learning_rate": 1.821393796522096e-05,
|
| 2001 |
+
"loss": 30.8007,
|
| 2002 |
+
"step": 25600
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.7609572664756871,
|
| 2006 |
+
"grad_norm": 7.750844955444336,
|
| 2007 |
+
"learning_rate": 1.7794341240235615e-05,
|
| 2008 |
+
"loss": 30.7227,
|
| 2009 |
+
"step": 25700
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.7639181896915458,
|
| 2013 |
+
"grad_norm": 7.581575870513916,
|
| 2014 |
+
"learning_rate": 1.737879111213961e-05,
|
| 2015 |
+
"loss": 30.6509,
|
| 2016 |
+
"step": 25800
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.7668791129074045,
|
| 2020 |
+
"grad_norm": 8.771635055541992,
|
| 2021 |
+
"learning_rate": 1.6967327423075142e-05,
|
| 2022 |
+
"loss": 30.7893,
|
| 2023 |
+
"step": 25900
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 0.7698400361232632,
|
| 2027 |
+
"grad_norm": 8.594512939453125,
|
| 2028 |
+
"learning_rate": 1.6559989623384456e-05,
|
| 2029 |
+
"loss": 30.6874,
|
| 2030 |
+
"step": 26000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.7698400361232632,
|
| 2034 |
+
"eval_loss": 3.7861363887786865,
|
| 2035 |
+
"eval_runtime": 112.2096,
|
| 2036 |
+
"eval_samples_per_second": 9.634,
|
| 2037 |
+
"eval_steps_per_second": 2.415,
|
| 2038 |
+
"step": 26000
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.772800959339122,
|
| 2042 |
+
"grad_norm": 7.919267177581787,
|
| 2043 |
+
"learning_rate": 1.615681676782755e-05,
|
| 2044 |
+
"loss": 30.7685,
|
| 2045 |
+
"step": 26100
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.7757618825549807,
|
| 2049 |
+
"grad_norm": 7.744143009185791,
|
| 2050 |
+
"learning_rate": 1.5757847511837648e-05,
|
| 2051 |
+
"loss": 30.7558,
|
| 2052 |
+
"step": 26200
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.7787228057708393,
|
| 2056 |
+
"grad_norm": 7.894962787628174,
|
| 2057 |
+
"learning_rate": 1.5363120107814955e-05,
|
| 2058 |
+
"loss": 30.7543,
|
| 2059 |
+
"step": 26300
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.781683728986698,
|
| 2063 |
+
"grad_norm": 9.573600769042969,
|
| 2064 |
+
"learning_rate": 1.4972672401459143e-05,
|
| 2065 |
+
"loss": 30.808,
|
| 2066 |
+
"step": 26400
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.7846446522025567,
|
| 2070 |
+
"grad_norm": 7.708218574523926,
|
| 2071 |
+
"learning_rate": 1.4586541828140706e-05,
|
| 2072 |
+
"loss": 30.6115,
|
| 2073 |
+
"step": 26500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.7876055754184155,
|
| 2077 |
+
"grad_norm": 8.170422554016113,
|
| 2078 |
+
"learning_rate": 1.4204765409311852e-05,
|
| 2079 |
+
"loss": 30.8811,
|
| 2080 |
+
"step": 26600
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.7905664986342742,
|
| 2084 |
+
"grad_norm": 8.293937683105469,
|
| 2085 |
+
"learning_rate": 1.3827379748956783e-05,
|
| 2086 |
+
"loss": 30.8484,
|
| 2087 |
+
"step": 26700
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.7935274218501329,
|
| 2091 |
+
"grad_norm": 7.64206075668335,
|
| 2092 |
+
"learning_rate": 1.3454421030082402e-05,
|
| 2093 |
+
"loss": 30.7768,
|
| 2094 |
+
"step": 26800
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.7964883450659915,
|
| 2098 |
+
"grad_norm": 7.780085563659668,
|
| 2099 |
+
"learning_rate": 1.3085925011248902e-05,
|
| 2100 |
+
"loss": 30.6903,
|
| 2101 |
+
"step": 26900
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.7994492682818503,
|
| 2105 |
+
"grad_norm": 7.651244640350342,
|
| 2106 |
+
"learning_rate": 1.2721927023141509e-05,
|
| 2107 |
+
"loss": 30.8888,
|
| 2108 |
+
"step": 27000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.7994492682818503,
|
| 2112 |
+
"eval_loss": 3.7866110801696777,
|
| 2113 |
+
"eval_runtime": 111.3993,
|
| 2114 |
+
"eval_samples_per_second": 9.704,
|
| 2115 |
+
"eval_steps_per_second": 2.433,
|
| 2116 |
+
"step": 27000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.802410191497709,
|
| 2120 |
+
"grad_norm": 7.893172740936279,
|
| 2121 |
+
"learning_rate": 1.2362461965182951e-05,
|
| 2122 |
+
"loss": 30.8551,
|
| 2123 |
+
"step": 27100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8053711147135677,
|
| 2127 |
+
"grad_norm": 8.348461151123047,
|
| 2128 |
+
"learning_rate": 1.2007564302187395e-05,
|
| 2129 |
+
"loss": 30.9086,
|
| 2130 |
+
"step": 27200
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.8083320379294264,
|
| 2134 |
+
"grad_norm": 8.005925178527832,
|
| 2135 |
+
"learning_rate": 1.1657268061055954e-05,
|
| 2136 |
+
"loss": 30.6258,
|
| 2137 |
+
"step": 27300
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.8112929611452852,
|
| 2141 |
+
"grad_norm": 7.919161319732666,
|
| 2142 |
+
"learning_rate": 1.1311606827514432e-05,
|
| 2143 |
+
"loss": 30.4614,
|
| 2144 |
+
"step": 27400
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.8142538843611438,
|
| 2148 |
+
"grad_norm": 8.806751251220703,
|
| 2149 |
+
"learning_rate": 1.0970613742892959e-05,
|
| 2150 |
+
"loss": 30.9882,
|
| 2151 |
+
"step": 27500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.8172148075770025,
|
| 2155 |
+
"grad_norm": 8.126434326171875,
|
| 2156 |
+
"learning_rate": 1.0634321500948665e-05,
|
| 2157 |
+
"loss": 30.6459,
|
| 2158 |
+
"step": 27600
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.8201757307928612,
|
| 2162 |
+
"grad_norm": 7.643808364868164,
|
| 2163 |
+
"learning_rate": 1.0302762344730893e-05,
|
| 2164 |
+
"loss": 30.6614,
|
| 2165 |
+
"step": 27700
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8231366540087199,
|
| 2169 |
+
"grad_norm": 8.046734809875488,
|
| 2170 |
+
"learning_rate": 9.97596806349001e-06,
|
| 2171 |
+
"loss": 30.6958,
|
| 2172 |
+
"step": 27800
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.8260975772245787,
|
| 2176 |
+
"grad_norm": 8.094582557678223,
|
| 2177 |
+
"learning_rate": 9.653969989629268e-06,
|
| 2178 |
+
"loss": 30.5807,
|
| 2179 |
+
"step": 27900
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8290585004404373,
|
| 2183 |
+
"grad_norm": 8.062453269958496,
|
| 2184 |
+
"learning_rate": 9.336798995700899e-06,
|
| 2185 |
+
"loss": 30.8323,
|
| 2186 |
+
"step": 28000
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.8290585004404373,
|
| 2190 |
+
"eval_loss": 3.786661386489868,
|
| 2191 |
+
"eval_runtime": 106.9454,
|
| 2192 |
+
"eval_samples_per_second": 10.108,
|
| 2193 |
+
"eval_steps_per_second": 2.534,
|
| 2194 |
+
"step": 28000
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.832019423656296,
|
| 2198 |
+
"grad_norm": 7.68911075592041,
|
| 2199 |
+
"learning_rate": 9.024485491446045e-06,
|
| 2200 |
+
"loss": 30.9853,
|
| 2201 |
+
"step": 28100
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.8349803468721547,
|
| 2205 |
+
"grad_norm": 7.82414436340332,
|
| 2206 |
+
"learning_rate": 8.717059420879143e-06,
|
| 2207 |
+
"loss": 30.5061,
|
| 2208 |
+
"step": 28200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.8379412700880134,
|
| 2212 |
+
"grad_norm": 7.392062664031982,
|
| 2213 |
+
"learning_rate": 8.414550259416917e-06,
|
| 2214 |
+
"loss": 30.9525,
|
| 2215 |
+
"step": 28300
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.8409021933038722,
|
| 2219 |
+
"grad_norm": 7.675992965698242,
|
| 2220 |
+
"learning_rate": 8.116987011052387e-06,
|
| 2221 |
+
"loss": 30.8296,
|
| 2222 |
+
"step": 28400
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.8438631165197309,
|
| 2226 |
+
"grad_norm": 8.038030624389648,
|
| 2227 |
+
"learning_rate": 7.824398205574006e-06,
|
| 2228 |
+
"loss": 30.8155,
|
| 2229 |
+
"step": 28500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.8468240397355895,
|
| 2233 |
+
"grad_norm": 7.427101135253906,
|
| 2234 |
+
"learning_rate": 7.536811895830222e-06,
|
| 2235 |
+
"loss": 30.9259,
|
| 2236 |
+
"step": 28600
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.8497849629514482,
|
| 2240 |
+
"grad_norm": 8.095186233520508,
|
| 2241 |
+
"learning_rate": 7.254255655039919e-06,
|
| 2242 |
+
"loss": 30.824,
|
| 2243 |
+
"step": 28700
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.852745886167307,
|
| 2247 |
+
"grad_norm": 7.521733283996582,
|
| 2248 |
+
"learning_rate": 6.9767565741486815e-06,
|
| 2249 |
+
"loss": 30.7226,
|
| 2250 |
+
"step": 28800
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.8557068093831657,
|
| 2254 |
+
"grad_norm": 7.494954586029053,
|
| 2255 |
+
"learning_rate": 6.704341259231415e-06,
|
| 2256 |
+
"loss": 30.7789,
|
| 2257 |
+
"step": 28900
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.8586677325990244,
|
| 2261 |
+
"grad_norm": 7.641082763671875,
|
| 2262 |
+
"learning_rate": 6.437035828941324e-06,
|
| 2263 |
+
"loss": 30.8001,
|
| 2264 |
+
"step": 29000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.8586677325990244,
|
| 2268 |
+
"eval_loss": 3.786005973815918,
|
| 2269 |
+
"eval_runtime": 111.1521,
|
| 2270 |
+
"eval_samples_per_second": 9.725,
|
| 2271 |
+
"eval_steps_per_second": 2.438,
|
| 2272 |
+
"step": 29000
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 0.8616286558148831,
|
| 2276 |
+
"grad_norm": 7.96475887298584,
|
| 2277 |
+
"learning_rate": 6.1748659120058386e-06,
|
| 2278 |
+
"loss": 30.8879,
|
| 2279 |
+
"step": 29100
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 0.8645895790307417,
|
| 2283 |
+
"grad_norm": 6.990954875946045,
|
| 2284 |
+
"learning_rate": 5.917856644769242e-06,
|
| 2285 |
+
"loss": 30.6077,
|
| 2286 |
+
"step": 29200
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.8675505022466005,
|
| 2290 |
+
"grad_norm": 7.170067310333252,
|
| 2291 |
+
"learning_rate": 5.666032668782735e-06,
|
| 2292 |
+
"loss": 30.8456,
|
| 2293 |
+
"step": 29300
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 0.8705114254624592,
|
| 2297 |
+
"grad_norm": 8.4426851272583,
|
| 2298 |
+
"learning_rate": 5.419418128441846e-06,
|
| 2299 |
+
"loss": 30.9228,
|
| 2300 |
+
"step": 29400
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.8734723486783179,
|
| 2304 |
+
"grad_norm": 8.034204483032227,
|
| 2305 |
+
"learning_rate": 5.178036668671475e-06,
|
| 2306 |
+
"loss": 30.7785,
|
| 2307 |
+
"step": 29500
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.8764332718941766,
|
| 2311 |
+
"grad_norm": 7.411805629730225,
|
| 2312 |
+
"learning_rate": 4.941911432658868e-06,
|
| 2313 |
+
"loss": 30.7495,
|
| 2314 |
+
"step": 29600
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.8793941951100354,
|
| 2318 |
+
"grad_norm": 7.887239456176758,
|
| 2319 |
+
"learning_rate": 4.7110650596347335e-06,
|
| 2320 |
+
"loss": 30.7797,
|
| 2321 |
+
"step": 29700
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.882355118325894,
|
| 2325 |
+
"grad_norm": 8.600279808044434,
|
| 2326 |
+
"learning_rate": 4.48551968270261e-06,
|
| 2327 |
+
"loss": 30.8267,
|
| 2328 |
+
"step": 29800
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.8853160415417527,
|
| 2332 |
+
"grad_norm": 8.055954933166504,
|
| 2333 |
+
"learning_rate": 4.26529692671679e-06,
|
| 2334 |
+
"loss": 30.8123,
|
| 2335 |
+
"step": 29900
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.8882769647576114,
|
| 2339 |
+
"grad_norm": 7.540750503540039,
|
| 2340 |
+
"learning_rate": 4.050417906208945e-06,
|
| 2341 |
+
"loss": 30.8866,
|
| 2342 |
+
"step": 30000
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.8882769647576114,
|
| 2346 |
+
"eval_loss": 3.7849574089050293,
|
| 2347 |
+
"eval_runtime": 108.0072,
|
| 2348 |
+
"eval_samples_per_second": 10.009,
|
| 2349 |
+
"eval_steps_per_second": 2.509,
|
| 2350 |
+
"step": 30000
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.8912378879734701,
|
| 2354 |
+
"grad_norm": 7.607705593109131,
|
| 2355 |
+
"learning_rate": 3.840903223363752e-06,
|
| 2356 |
+
"loss": 30.7932,
|
| 2357 |
+
"step": 30100
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.8941988111893289,
|
| 2361 |
+
"grad_norm": 7.834300518035889,
|
| 2362 |
+
"learning_rate": 3.636772966043571e-06,
|
| 2363 |
+
"loss": 30.6935,
|
| 2364 |
+
"step": 30200
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.8971597344051876,
|
| 2368 |
+
"grad_norm": 9.865922927856445,
|
| 2369 |
+
"learning_rate": 3.4380467058624585e-06,
|
| 2370 |
+
"loss": 30.5129,
|
| 2371 |
+
"step": 30300
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.9001206576210462,
|
| 2375 |
+
"grad_norm": 7.9707865715026855,
|
| 2376 |
+
"learning_rate": 3.244743496309701e-06,
|
| 2377 |
+
"loss": 30.8035,
|
| 2378 |
+
"step": 30400
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.9030815808369049,
|
| 2382 |
+
"grad_norm": 8.035768508911133,
|
| 2383 |
+
"learning_rate": 3.0568818709229364e-06,
|
| 2384 |
+
"loss": 30.4973,
|
| 2385 |
+
"step": 30500
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.9060425040527637,
|
| 2389 |
+
"grad_norm": 8.816192626953125,
|
| 2390 |
+
"learning_rate": 2.8744798415113015e-06,
|
| 2391 |
+
"loss": 30.5553,
|
| 2392 |
+
"step": 30600
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.9090034272686224,
|
| 2396 |
+
"grad_norm": 7.411801338195801,
|
| 2397 |
+
"learning_rate": 2.6975548964283823e-06,
|
| 2398 |
+
"loss": 30.6758,
|
| 2399 |
+
"step": 30700
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.9119643504844811,
|
| 2403 |
+
"grad_norm": 7.46308708190918,
|
| 2404 |
+
"learning_rate": 2.5261239988955733e-06,
|
| 2405 |
+
"loss": 30.8337,
|
| 2406 |
+
"step": 30800
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.9149252737003397,
|
| 2410 |
+
"grad_norm": 8.57913875579834,
|
| 2411 |
+
"learning_rate": 2.360203585375571e-06,
|
| 2412 |
+
"loss": 31.0671,
|
| 2413 |
+
"step": 30900
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.9178861969161984,
|
| 2417 |
+
"grad_norm": 7.983087062835693,
|
| 2418 |
+
"learning_rate": 2.1998095639965577e-06,
|
| 2419 |
+
"loss": 30.913,
|
| 2420 |
+
"step": 31000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.9178861969161984,
|
| 2424 |
+
"eval_loss": 3.785719394683838,
|
| 2425 |
+
"eval_runtime": 110.9703,
|
| 2426 |
+
"eval_samples_per_second": 9.741,
|
| 2427 |
+
"eval_steps_per_second": 2.442,
|
| 2428 |
+
"step": 31000
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 0.9208471201320572,
|
| 2432 |
+
"grad_norm": 8.11637020111084,
|
| 2433 |
+
"learning_rate": 2.044957313026925e-06,
|
| 2434 |
+
"loss": 30.7294,
|
| 2435 |
+
"step": 31100
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.9238080433479159,
|
| 2439 |
+
"grad_norm": 7.882040977478027,
|
| 2440 |
+
"learning_rate": 1.895661679400842e-06,
|
| 2441 |
+
"loss": 30.7816,
|
| 2442 |
+
"step": 31200
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.9267689665637746,
|
| 2446 |
+
"grad_norm": 7.475772857666016,
|
| 2447 |
+
"learning_rate": 1.7519369772947525e-06,
|
| 2448 |
+
"loss": 30.5198,
|
| 2449 |
+
"step": 31300
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.9297298897796333,
|
| 2453 |
+
"grad_norm": 8.094454765319824,
|
| 2454 |
+
"learning_rate": 1.6137969867549674e-06,
|
| 2455 |
+
"loss": 30.8313,
|
| 2456 |
+
"step": 31400
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.932690812995492,
|
| 2460 |
+
"grad_norm": 8.635899543762207,
|
| 2461 |
+
"learning_rate": 1.4812549523764674e-06,
|
| 2462 |
+
"loss": 30.6539,
|
| 2463 |
+
"step": 31500
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 0.9356517362113507,
|
| 2467 |
+
"grad_norm": 7.975414752960205,
|
| 2468 |
+
"learning_rate": 1.354323582033039e-06,
|
| 2469 |
+
"loss": 30.5804,
|
| 2470 |
+
"step": 31600
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 0.9386126594272094,
|
| 2474 |
+
"grad_norm": 7.660233020782471,
|
| 2475 |
+
"learning_rate": 1.233015045658823e-06,
|
| 2476 |
+
"loss": 30.6357,
|
| 2477 |
+
"step": 31700
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 0.9415735826430681,
|
| 2481 |
+
"grad_norm": 8.09595012664795,
|
| 2482 |
+
"learning_rate": 1.1173409740815532e-06,
|
| 2483 |
+
"loss": 30.7201,
|
| 2484 |
+
"step": 31800
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.9445345058589268,
|
| 2488 |
+
"grad_norm": 8.44491958618164,
|
| 2489 |
+
"learning_rate": 1.0073124579073701e-06,
|
| 2490 |
+
"loss": 30.7462,
|
| 2491 |
+
"step": 31900
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.9474954290747856,
|
| 2495 |
+
"grad_norm": 8.275026321411133,
|
| 2496 |
+
"learning_rate": 9.0294004645749e-07,
|
| 2497 |
+
"loss": 30.7256,
|
| 2498 |
+
"step": 32000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.9474954290747856,
|
| 2502 |
+
"eval_loss": 3.7850279808044434,
|
| 2503 |
+
"eval_runtime": 109.0824,
|
| 2504 |
+
"eval_samples_per_second": 9.91,
|
| 2505 |
+
"eval_steps_per_second": 2.484,
|
| 2506 |
+
"step": 32000
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.9504563522906442,
|
| 2510 |
+
"grad_norm": 7.571169376373291,
|
| 2511 |
+
"learning_rate": 8.042337467567484e-07,
|
| 2512 |
+
"loss": 30.7194,
|
| 2513 |
+
"step": 32100
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 0.9534172755065029,
|
| 2517 |
+
"grad_norm": 8.020681381225586,
|
| 2518 |
+
"learning_rate": 7.112030225741472e-07,
|
| 2519 |
+
"loss": 30.5828,
|
| 2520 |
+
"step": 32200
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 0.9563781987223616,
|
| 2524 |
+
"grad_norm": 7.482342720031738,
|
| 2525 |
+
"learning_rate": 6.238567935155004e-07,
|
| 2526 |
+
"loss": 30.5888,
|
| 2527 |
+
"step": 32300
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 0.9593391219382204,
|
| 2531 |
+
"grad_norm": 8.336071014404297,
|
| 2532 |
+
"learning_rate": 5.422034341682314e-07,
|
| 2533 |
+
"loss": 30.858,
|
| 2534 |
+
"step": 32400
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.9623000451540791,
|
| 2538 |
+
"grad_norm": 7.819650173187256,
|
| 2539 |
+
"learning_rate": 4.6625077329842224e-07,
|
| 2540 |
+
"loss": 30.6983,
|
| 2541 |
+
"step": 32500
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 0.9652609683699378,
|
| 2545 |
+
"grad_norm": 8.101078987121582,
|
| 2546 |
+
"learning_rate": 3.960060931002141e-07,
|
| 2547 |
+
"loss": 30.7803,
|
| 2548 |
+
"step": 32600
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 0.9682218915857964,
|
| 2552 |
+
"grad_norm": 9.275129318237305,
|
| 2553 |
+
"learning_rate": 3.3147612849762533e-07,
|
| 2554 |
+
"loss": 30.8961,
|
| 2555 |
+
"step": 32700
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 0.9711828148016551,
|
| 2559 |
+
"grad_norm": 8.00763988494873,
|
| 2560 |
+
"learning_rate": 2.7266706649877516e-07,
|
| 2561 |
+
"loss": 30.9344,
|
| 2562 |
+
"step": 32800
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 0.9741437380175139,
|
| 2566 |
+
"grad_norm": 8.840792655944824,
|
| 2567 |
+
"learning_rate": 2.1958454560274455e-07,
|
| 2568 |
+
"loss": 30.7027,
|
| 2569 |
+
"step": 32900
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 0.9771046612333726,
|
| 2573 |
+
"grad_norm": 8.015409469604492,
|
| 2574 |
+
"learning_rate": 1.722336552589021e-07,
|
| 2575 |
+
"loss": 30.7569,
|
| 2576 |
+
"step": 33000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.9771046612333726,
|
| 2580 |
+
"eval_loss": 3.785550117492676,
|
| 2581 |
+
"eval_runtime": 109.3256,
|
| 2582 |
+
"eval_samples_per_second": 9.888,
|
| 2583 |
+
"eval_steps_per_second": 2.479,
|
| 2584 |
+
"step": 33000
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 0.9800655844492313,
|
| 2588 |
+
"grad_norm": 8.226040840148926,
|
| 2589 |
+
"learning_rate": 1.3061893537898773e-07,
|
| 2590 |
+
"loss": 30.6858,
|
| 2591 |
+
"step": 33100
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.9830265076650899,
|
| 2595 |
+
"grad_norm": 7.274777889251709,
|
| 2596 |
+
"learning_rate": 9.474437590182072e-08,
|
| 2597 |
+
"loss": 30.701,
|
| 2598 |
+
"step": 33200
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 0.9859874308809486,
|
| 2602 |
+
"grad_norm": 7.866406440734863,
|
| 2603 |
+
"learning_rate": 6.46134164107326e-08,
|
| 2604 |
+
"loss": 30.6392,
|
| 2605 |
+
"step": 33300
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.9889483540968074,
|
| 2609 |
+
"grad_norm": 7.722043514251709,
|
| 2610 |
+
"learning_rate": 4.022894580381742e-08,
|
| 2611 |
+
"loss": 30.8502,
|
| 2612 |
+
"step": 33400
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.9919092773126661,
|
| 2616 |
+
"grad_norm": 7.612312316894531,
|
| 2617 |
+
"learning_rate": 2.1593302016933437e-08,
|
| 2618 |
+
"loss": 30.7914,
|
| 2619 |
+
"step": 33500
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.9948702005285248,
|
| 2623 |
+
"grad_norm": 8.195243835449219,
|
| 2624 |
+
"learning_rate": 8.708271799542367e-09,
|
| 2625 |
+
"loss": 30.8885,
|
| 2626 |
+
"step": 33600
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.9978311237443835,
|
| 2630 |
+
"grad_norm": 8.127638816833496,
|
| 2631 |
+
"learning_rate": 1.5750905434130935e-09,
|
| 2632 |
+
"loss": 30.9894,
|
| 2633 |
+
"step": 33700
|
| 2634 |
+
}
|
| 2635 |
+
],
|
| 2636 |
+
"logging_steps": 100,
|
| 2637 |
+
"max_steps": 33773,
|
| 2638 |
+
"num_input_tokens_seen": 0,
|
| 2639 |
+
"num_train_epochs": 1,
|
| 2640 |
+
"save_steps": 500,
|
| 2641 |
+
"stateful_callbacks": {
|
| 2642 |
+
"TrainerControl": {
|
| 2643 |
+
"args": {
|
| 2644 |
+
"should_epoch_stop": false,
|
| 2645 |
+
"should_evaluate": false,
|
| 2646 |
+
"should_log": false,
|
| 2647 |
+
"should_save": true,
|
| 2648 |
+
"should_training_stop": true
|
| 2649 |
+
},
|
| 2650 |
+
"attributes": {}
|
| 2651 |
+
}
|
| 2652 |
+
},
|
| 2653 |
+
"total_flos": 5.598282561239384e+18,
|
| 2654 |
+
"train_batch_size": 4,
|
| 2655 |
+
"trial_name": null,
|
| 2656 |
+
"trial_params": null
|
| 2657 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c7abecf39843cd0ef9dea5e194fc495c60905578d8e9c6fafa20b2cc00b4dfc
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|