Upload folder using huggingface_hub
Browse files- checkpoint-2250/config.json +32 -0
- checkpoint-2250/generation_config.json +7 -0
- checkpoint-2250/model.safetensors +3 -0
- checkpoint-2250/optimizer.pt +3 -0
- checkpoint-2250/rng_state.pth +3 -0
- checkpoint-2250/scheduler.pt +3 -0
- checkpoint-2250/trainer_state.json +1608 -0
- checkpoint-2250/training_args.bin +3 -0
- config.json +32 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- training_args.bin +3 -0
checkpoint-2250/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco-plus",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 26,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.46.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
checkpoint-2250/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.46.2"
|
| 7 |
+
}
|
checkpoint-2250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e7be3ecd6b2779ed54c53d5fbba0e115f498f10873208dfc88d3fa866cb0b10
|
| 3 |
+
size 3092603344
|
checkpoint-2250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e343f59088ba773f36f024a274d62694c670324510ceeffecc6bed7606df5a0f
|
| 3 |
+
size 6185356034
|
checkpoint-2250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-2250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27398485596dd8b226b660b87df6dbe00dc04b9a27d13177c65b43b5c27af097
|
| 3 |
+
size 1064
|
checkpoint-2250/trainer_state.json
ADDED
|
@@ -0,0 +1,1608 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 2250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0044444444444444444,
|
| 13 |
+
"grad_norm": 172.13922119140625,
|
| 14 |
+
"learning_rate": 5.000000000000001e-07,
|
| 15 |
+
"loss": 11.5329,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008888888888888889,
|
| 20 |
+
"grad_norm": 179.96237182617188,
|
| 21 |
+
"learning_rate": 1.5e-06,
|
| 22 |
+
"loss": 11.3904,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013333333333333334,
|
| 27 |
+
"grad_norm": 1364.69921875,
|
| 28 |
+
"learning_rate": 2.5e-06,
|
| 29 |
+
"loss": 10.7917,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.017777777777777778,
|
| 34 |
+
"grad_norm": 8219.5224609375,
|
| 35 |
+
"learning_rate": 3.3e-06,
|
| 36 |
+
"loss": 9.1512,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.022222222222222223,
|
| 41 |
+
"grad_norm": 12965.9892578125,
|
| 42 |
+
"learning_rate": 4.2999999999999995e-06,
|
| 43 |
+
"loss": 7.8213,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02666666666666667,
|
| 48 |
+
"grad_norm": 31872.74609375,
|
| 49 |
+
"learning_rate": 5.3e-06,
|
| 50 |
+
"loss": 6.6272,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03111111111111111,
|
| 55 |
+
"grad_norm": 788.8919677734375,
|
| 56 |
+
"learning_rate": 6.300000000000001e-06,
|
| 57 |
+
"loss": 6.3266,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.035555555555555556,
|
| 62 |
+
"grad_norm": 106.24903869628906,
|
| 63 |
+
"learning_rate": 7.2999999999999996e-06,
|
| 64 |
+
"loss": 5.7356,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"grad_norm": 409.2347412109375,
|
| 70 |
+
"learning_rate": 8.3e-06,
|
| 71 |
+
"loss": 5.018,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.044444444444444446,
|
| 76 |
+
"grad_norm": 817.6410522460938,
|
| 77 |
+
"learning_rate": 9.3e-06,
|
| 78 |
+
"loss": 5.422,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04888888888888889,
|
| 83 |
+
"grad_norm": 589.453125,
|
| 84 |
+
"learning_rate": 1.03e-05,
|
| 85 |
+
"loss": 3.6104,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05333333333333334,
|
| 90 |
+
"grad_norm": 299.5021667480469,
|
| 91 |
+
"learning_rate": 1.13e-05,
|
| 92 |
+
"loss": 3.3433,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.057777777777777775,
|
| 97 |
+
"grad_norm": 105.66629791259766,
|
| 98 |
+
"learning_rate": 1.23e-05,
|
| 99 |
+
"loss": 2.1184,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06222222222222222,
|
| 104 |
+
"grad_norm": 94.36296844482422,
|
| 105 |
+
"learning_rate": 1.3300000000000001e-05,
|
| 106 |
+
"loss": 1.6441,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06666666666666667,
|
| 111 |
+
"grad_norm": 99.46455383300781,
|
| 112 |
+
"learning_rate": 1.43e-05,
|
| 113 |
+
"loss": 1.0691,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07111111111111111,
|
| 118 |
+
"grad_norm": 128.905517578125,
|
| 119 |
+
"learning_rate": 1.53e-05,
|
| 120 |
+
"loss": 1.347,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07555555555555556,
|
| 125 |
+
"grad_norm": 10.669831275939941,
|
| 126 |
+
"learning_rate": 1.63e-05,
|
| 127 |
+
"loss": 0.8163,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08,
|
| 132 |
+
"grad_norm": 17.684833526611328,
|
| 133 |
+
"learning_rate": 1.73e-05,
|
| 134 |
+
"loss": 1.0315,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08444444444444445,
|
| 139 |
+
"grad_norm": 35.8447151184082,
|
| 140 |
+
"learning_rate": 1.83e-05,
|
| 141 |
+
"loss": 0.6946,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08888888888888889,
|
| 146 |
+
"grad_norm": 88.678466796875,
|
| 147 |
+
"learning_rate": 1.93e-05,
|
| 148 |
+
"loss": 1.0834,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09333333333333334,
|
| 153 |
+
"grad_norm": 50.5704231262207,
|
| 154 |
+
"learning_rate": 2.0300000000000002e-05,
|
| 155 |
+
"loss": 0.9062,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09777777777777778,
|
| 160 |
+
"grad_norm": 5.56904935836792,
|
| 161 |
+
"learning_rate": 2.13e-05,
|
| 162 |
+
"loss": 0.9961,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10222222222222223,
|
| 167 |
+
"grad_norm": 2.848574638366699,
|
| 168 |
+
"learning_rate": 2.23e-05,
|
| 169 |
+
"loss": 0.7547,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.10666666666666667,
|
| 174 |
+
"grad_norm": 51.646854400634766,
|
| 175 |
+
"learning_rate": 2.3300000000000004e-05,
|
| 176 |
+
"loss": 0.9434,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1111111111111111,
|
| 181 |
+
"grad_norm": 4.968932151794434,
|
| 182 |
+
"learning_rate": 2.43e-05,
|
| 183 |
+
"loss": 0.9282,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.11555555555555555,
|
| 188 |
+
"grad_norm": 8.864336967468262,
|
| 189 |
+
"learning_rate": 2.5300000000000002e-05,
|
| 190 |
+
"loss": 1.1923,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12,
|
| 195 |
+
"grad_norm": 6.225351333618164,
|
| 196 |
+
"learning_rate": 2.6300000000000002e-05,
|
| 197 |
+
"loss": 0.7519,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12444444444444444,
|
| 202 |
+
"grad_norm": 16.043298721313477,
|
| 203 |
+
"learning_rate": 2.7300000000000003e-05,
|
| 204 |
+
"loss": 0.8965,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1288888888888889,
|
| 209 |
+
"grad_norm": 13.324910163879395,
|
| 210 |
+
"learning_rate": 2.83e-05,
|
| 211 |
+
"loss": 0.8238,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13333333333333333,
|
| 216 |
+
"grad_norm": 3.661782741546631,
|
| 217 |
+
"learning_rate": 2.93e-05,
|
| 218 |
+
"loss": 0.6619,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.13777777777777778,
|
| 223 |
+
"grad_norm": 24.01588249206543,
|
| 224 |
+
"learning_rate": 3.03e-05,
|
| 225 |
+
"loss": 0.9874,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14222222222222222,
|
| 230 |
+
"grad_norm": 3.4116015434265137,
|
| 231 |
+
"learning_rate": 3.13e-05,
|
| 232 |
+
"loss": 0.7866,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.14666666666666667,
|
| 237 |
+
"grad_norm": 5.378733158111572,
|
| 238 |
+
"learning_rate": 3.2300000000000006e-05,
|
| 239 |
+
"loss": 0.784,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1511111111111111,
|
| 244 |
+
"grad_norm": 3.0666747093200684,
|
| 245 |
+
"learning_rate": 3.33e-05,
|
| 246 |
+
"loss": 0.8068,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.15555555555555556,
|
| 251 |
+
"grad_norm": 5.233002662658691,
|
| 252 |
+
"learning_rate": 3.430000000000001e-05,
|
| 253 |
+
"loss": 0.8338,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16,
|
| 258 |
+
"grad_norm": 12.038925170898438,
|
| 259 |
+
"learning_rate": 3.53e-05,
|
| 260 |
+
"loss": 0.9978,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.16444444444444445,
|
| 265 |
+
"grad_norm": 4.42678165435791,
|
| 266 |
+
"learning_rate": 3.63e-05,
|
| 267 |
+
"loss": 0.9186,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1688888888888889,
|
| 272 |
+
"grad_norm": 3.2533979415893555,
|
| 273 |
+
"learning_rate": 3.73e-05,
|
| 274 |
+
"loss": 0.853,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.17333333333333334,
|
| 279 |
+
"grad_norm": 6.089888095855713,
|
| 280 |
+
"learning_rate": 3.83e-05,
|
| 281 |
+
"loss": 0.6885,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.17777777777777778,
|
| 286 |
+
"grad_norm": 2.185434341430664,
|
| 287 |
+
"learning_rate": 3.9300000000000007e-05,
|
| 288 |
+
"loss": 0.7051,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.18222222222222223,
|
| 293 |
+
"grad_norm": 3.463395118713379,
|
| 294 |
+
"learning_rate": 4.0300000000000004e-05,
|
| 295 |
+
"loss": 0.7594,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.18666666666666668,
|
| 300 |
+
"grad_norm": 111.5975341796875,
|
| 301 |
+
"learning_rate": 4.13e-05,
|
| 302 |
+
"loss": 0.7679,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.19111111111111112,
|
| 307 |
+
"grad_norm": 2.420258045196533,
|
| 308 |
+
"learning_rate": 4.23e-05,
|
| 309 |
+
"loss": 0.9897,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.19555555555555557,
|
| 314 |
+
"grad_norm": 3.507974863052368,
|
| 315 |
+
"learning_rate": 4.33e-05,
|
| 316 |
+
"loss": 0.7764,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2,
|
| 321 |
+
"grad_norm": 1.6020970344543457,
|
| 322 |
+
"learning_rate": 4.43e-05,
|
| 323 |
+
"loss": 0.6163,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.20444444444444446,
|
| 328 |
+
"grad_norm": 1.9605637788772583,
|
| 329 |
+
"learning_rate": 4.53e-05,
|
| 330 |
+
"loss": 0.9071,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2088888888888889,
|
| 335 |
+
"grad_norm": 6.756528377532959,
|
| 336 |
+
"learning_rate": 4.630000000000001e-05,
|
| 337 |
+
"loss": 0.939,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.21333333333333335,
|
| 342 |
+
"grad_norm": 6.34450101852417,
|
| 343 |
+
"learning_rate": 4.73e-05,
|
| 344 |
+
"loss": 0.832,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.21777777777777776,
|
| 349 |
+
"grad_norm": 3.8294358253479004,
|
| 350 |
+
"learning_rate": 4.83e-05,
|
| 351 |
+
"loss": 0.9205,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2222222222222222,
|
| 356 |
+
"grad_norm": 2.1834263801574707,
|
| 357 |
+
"learning_rate": 4.93e-05,
|
| 358 |
+
"loss": 0.6335,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.22666666666666666,
|
| 363 |
+
"grad_norm": 2.837082624435425,
|
| 364 |
+
"learning_rate": 4.9914285714285717e-05,
|
| 365 |
+
"loss": 0.6933,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2311111111111111,
|
| 370 |
+
"grad_norm": 1.8396414518356323,
|
| 371 |
+
"learning_rate": 4.962857142857143e-05,
|
| 372 |
+
"loss": 1.0322,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.23555555555555555,
|
| 377 |
+
"grad_norm": 4.330628871917725,
|
| 378 |
+
"learning_rate": 4.934285714285715e-05,
|
| 379 |
+
"loss": 0.7124,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.24,
|
| 384 |
+
"grad_norm": 2.490299701690674,
|
| 385 |
+
"learning_rate": 4.905714285714286e-05,
|
| 386 |
+
"loss": 0.7426,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.24444444444444444,
|
| 391 |
+
"grad_norm": 1.341838002204895,
|
| 392 |
+
"learning_rate": 4.8771428571428574e-05,
|
| 393 |
+
"loss": 0.7588,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.24888888888888888,
|
| 398 |
+
"grad_norm": 2.234884262084961,
|
| 399 |
+
"learning_rate": 4.848571428571429e-05,
|
| 400 |
+
"loss": 0.8314,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.25333333333333335,
|
| 405 |
+
"grad_norm": 2.8187923431396484,
|
| 406 |
+
"learning_rate": 4.82e-05,
|
| 407 |
+
"loss": 0.8109,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2577777777777778,
|
| 412 |
+
"grad_norm": 0.9691933393478394,
|
| 413 |
+
"learning_rate": 4.7914285714285715e-05,
|
| 414 |
+
"loss": 0.6785,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.26222222222222225,
|
| 419 |
+
"grad_norm": 1.8897961378097534,
|
| 420 |
+
"learning_rate": 4.762857142857143e-05,
|
| 421 |
+
"loss": 0.9523,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.26666666666666666,
|
| 426 |
+
"grad_norm": 7.316945552825928,
|
| 427 |
+
"learning_rate": 4.734285714285715e-05,
|
| 428 |
+
"loss": 0.5996,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.27111111111111114,
|
| 433 |
+
"grad_norm": 2.491607427597046,
|
| 434 |
+
"learning_rate": 4.7057142857142864e-05,
|
| 435 |
+
"loss": 0.5426,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.27555555555555555,
|
| 440 |
+
"grad_norm": 2.7054076194763184,
|
| 441 |
+
"learning_rate": 4.677142857142857e-05,
|
| 442 |
+
"loss": 0.6294,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.28,
|
| 447 |
+
"grad_norm": 1.5034236907958984,
|
| 448 |
+
"learning_rate": 4.648571428571429e-05,
|
| 449 |
+
"loss": 0.4571,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.28444444444444444,
|
| 454 |
+
"grad_norm": 5.013509750366211,
|
| 455 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 456 |
+
"loss": 0.9696,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.28888888888888886,
|
| 461 |
+
"grad_norm": 1.4784796237945557,
|
| 462 |
+
"learning_rate": 4.5914285714285714e-05,
|
| 463 |
+
"loss": 0.79,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.29333333333333333,
|
| 468 |
+
"grad_norm": 1.679485559463501,
|
| 469 |
+
"learning_rate": 4.562857142857143e-05,
|
| 470 |
+
"loss": 0.5445,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.29777777777777775,
|
| 475 |
+
"grad_norm": 11.93566608428955,
|
| 476 |
+
"learning_rate": 4.534285714285714e-05,
|
| 477 |
+
"loss": 0.8077,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3022222222222222,
|
| 482 |
+
"grad_norm": 2.100651264190674,
|
| 483 |
+
"learning_rate": 4.5057142857142856e-05,
|
| 484 |
+
"loss": 0.5643,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.30666666666666664,
|
| 489 |
+
"grad_norm": 2.368565797805786,
|
| 490 |
+
"learning_rate": 4.477142857142858e-05,
|
| 491 |
+
"loss": 1.0012,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3111111111111111,
|
| 496 |
+
"grad_norm": 2.4255175590515137,
|
| 497 |
+
"learning_rate": 4.448571428571429e-05,
|
| 498 |
+
"loss": 0.6344,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.31555555555555553,
|
| 503 |
+
"grad_norm": 3.4809205532073975,
|
| 504 |
+
"learning_rate": 4.4200000000000004e-05,
|
| 505 |
+
"loss": 0.87,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.32,
|
| 510 |
+
"grad_norm": 12.76645565032959,
|
| 511 |
+
"learning_rate": 4.391428571428572e-05,
|
| 512 |
+
"loss": 0.673,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3244444444444444,
|
| 517 |
+
"grad_norm": 3.417945623397827,
|
| 518 |
+
"learning_rate": 4.362857142857143e-05,
|
| 519 |
+
"loss": 0.6753,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3288888888888889,
|
| 524 |
+
"grad_norm": 2.9550516605377197,
|
| 525 |
+
"learning_rate": 4.3342857142857145e-05,
|
| 526 |
+
"loss": 0.6621,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3333333333333333,
|
| 531 |
+
"grad_norm": 1.9887003898620605,
|
| 532 |
+
"learning_rate": 4.3057142857142854e-05,
|
| 533 |
+
"loss": 0.671,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3377777777777778,
|
| 538 |
+
"grad_norm": 1.826278567314148,
|
| 539 |
+
"learning_rate": 4.277142857142857e-05,
|
| 540 |
+
"loss": 0.7536,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3422222222222222,
|
| 545 |
+
"grad_norm": 4.41416597366333,
|
| 546 |
+
"learning_rate": 4.2485714285714286e-05,
|
| 547 |
+
"loss": 0.7106,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3466666666666667,
|
| 552 |
+
"grad_norm": 1.8409727811813354,
|
| 553 |
+
"learning_rate": 4.22e-05,
|
| 554 |
+
"loss": 0.7142,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3511111111111111,
|
| 559 |
+
"grad_norm": 2.143974781036377,
|
| 560 |
+
"learning_rate": 4.191428571428572e-05,
|
| 561 |
+
"loss": 0.5623,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.35555555555555557,
|
| 566 |
+
"grad_norm": 1.1921825408935547,
|
| 567 |
+
"learning_rate": 4.162857142857143e-05,
|
| 568 |
+
"loss": 0.6638,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.36,
|
| 573 |
+
"grad_norm": 2.4289398193359375,
|
| 574 |
+
"learning_rate": 4.1342857142857144e-05,
|
| 575 |
+
"loss": 0.503,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.36444444444444446,
|
| 580 |
+
"grad_norm": 1.718072533607483,
|
| 581 |
+
"learning_rate": 4.105714285714286e-05,
|
| 582 |
+
"loss": 0.4197,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3688888888888889,
|
| 587 |
+
"grad_norm": 2.278563976287842,
|
| 588 |
+
"learning_rate": 4.077142857142857e-05,
|
| 589 |
+
"loss": 0.611,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.37333333333333335,
|
| 594 |
+
"grad_norm": 2.060332775115967,
|
| 595 |
+
"learning_rate": 4.0485714285714285e-05,
|
| 596 |
+
"loss": 0.5883,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.37777777777777777,
|
| 601 |
+
"grad_norm": 2.5066239833831787,
|
| 602 |
+
"learning_rate": 4.02e-05,
|
| 603 |
+
"loss": 0.6179,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.38222222222222224,
|
| 608 |
+
"grad_norm": 5.195372104644775,
|
| 609 |
+
"learning_rate": 3.991428571428572e-05,
|
| 610 |
+
"loss": 0.7709,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.38666666666666666,
|
| 615 |
+
"grad_norm": 3.0029399394989014,
|
| 616 |
+
"learning_rate": 3.9628571428571433e-05,
|
| 617 |
+
"loss": 0.584,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.39111111111111113,
|
| 622 |
+
"grad_norm": 6.307543754577637,
|
| 623 |
+
"learning_rate": 3.934285714285714e-05,
|
| 624 |
+
"loss": 0.6633,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.39555555555555555,
|
| 629 |
+
"grad_norm": 6.635744571685791,
|
| 630 |
+
"learning_rate": 3.905714285714286e-05,
|
| 631 |
+
"loss": 0.85,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4,
|
| 636 |
+
"grad_norm": 4.6865434646606445,
|
| 637 |
+
"learning_rate": 3.8771428571428575e-05,
|
| 638 |
+
"loss": 0.6508,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.40444444444444444,
|
| 643 |
+
"grad_norm": 1.8700509071350098,
|
| 644 |
+
"learning_rate": 3.8485714285714284e-05,
|
| 645 |
+
"loss": 0.5405,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4088888888888889,
|
| 650 |
+
"grad_norm": 3.749453067779541,
|
| 651 |
+
"learning_rate": 3.82e-05,
|
| 652 |
+
"loss": 0.6869,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.41333333333333333,
|
| 657 |
+
"grad_norm": 2.443854570388794,
|
| 658 |
+
"learning_rate": 3.7914285714285716e-05,
|
| 659 |
+
"loss": 0.5013,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4177777777777778,
|
| 664 |
+
"grad_norm": 1.066603183746338,
|
| 665 |
+
"learning_rate": 3.762857142857143e-05,
|
| 666 |
+
"loss": 0.5993,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4222222222222222,
|
| 671 |
+
"grad_norm": 5.453496932983398,
|
| 672 |
+
"learning_rate": 3.734285714285715e-05,
|
| 673 |
+
"loss": 0.633,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4266666666666667,
|
| 678 |
+
"grad_norm": 3.3490309715270996,
|
| 679 |
+
"learning_rate": 3.705714285714286e-05,
|
| 680 |
+
"loss": 0.7452,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4311111111111111,
|
| 685 |
+
"grad_norm": 2.070544719696045,
|
| 686 |
+
"learning_rate": 3.6771428571428574e-05,
|
| 687 |
+
"loss": 0.7698,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.43555555555555553,
|
| 692 |
+
"grad_norm": 3.1262307167053223,
|
| 693 |
+
"learning_rate": 3.648571428571429e-05,
|
| 694 |
+
"loss": 0.7202,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.44,
|
| 699 |
+
"grad_norm": 4.966836929321289,
|
| 700 |
+
"learning_rate": 3.62e-05,
|
| 701 |
+
"loss": 0.6881,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4444444444444444,
|
| 706 |
+
"grad_norm": 0.9398611783981323,
|
| 707 |
+
"learning_rate": 3.5914285714285715e-05,
|
| 708 |
+
"loss": 0.3937,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4488888888888889,
|
| 713 |
+
"grad_norm": 2.2783327102661133,
|
| 714 |
+
"learning_rate": 3.562857142857143e-05,
|
| 715 |
+
"loss": 0.5421,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4533333333333333,
|
| 720 |
+
"grad_norm": 1.5350534915924072,
|
| 721 |
+
"learning_rate": 3.534285714285715e-05,
|
| 722 |
+
"loss": 1.1952,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4577777777777778,
|
| 727 |
+
"grad_norm": 2.5785741806030273,
|
| 728 |
+
"learning_rate": 3.505714285714286e-05,
|
| 729 |
+
"loss": 0.7421,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4622222222222222,
|
| 734 |
+
"grad_norm": 3.4625842571258545,
|
| 735 |
+
"learning_rate": 3.477142857142857e-05,
|
| 736 |
+
"loss": 0.6769,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.4666666666666667,
|
| 741 |
+
"grad_norm": 1.2348237037658691,
|
| 742 |
+
"learning_rate": 3.448571428571429e-05,
|
| 743 |
+
"loss": 0.4613,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4711111111111111,
|
| 748 |
+
"grad_norm": 1.4216806888580322,
|
| 749 |
+
"learning_rate": 3.4200000000000005e-05,
|
| 750 |
+
"loss": 0.6116,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.47555555555555556,
|
| 755 |
+
"grad_norm": 1.089032769203186,
|
| 756 |
+
"learning_rate": 3.3914285714285714e-05,
|
| 757 |
+
"loss": 0.5686,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.48,
|
| 762 |
+
"grad_norm": 2.135321855545044,
|
| 763 |
+
"learning_rate": 3.362857142857143e-05,
|
| 764 |
+
"loss": 0.5668,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.48444444444444446,
|
| 769 |
+
"grad_norm": 1.846582055091858,
|
| 770 |
+
"learning_rate": 3.334285714285714e-05,
|
| 771 |
+
"loss": 0.62,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.4888888888888889,
|
| 776 |
+
"grad_norm": 2.3308606147766113,
|
| 777 |
+
"learning_rate": 3.305714285714286e-05,
|
| 778 |
+
"loss": 0.7323,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.49333333333333335,
|
| 783 |
+
"grad_norm": 10.256339073181152,
|
| 784 |
+
"learning_rate": 3.277142857142858e-05,
|
| 785 |
+
"loss": 0.6122,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.49777777777777776,
|
| 790 |
+
"grad_norm": 5.60221529006958,
|
| 791 |
+
"learning_rate": 3.248571428571429e-05,
|
| 792 |
+
"loss": 0.7023,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5022222222222222,
|
| 797 |
+
"grad_norm": 1.3172476291656494,
|
| 798 |
+
"learning_rate": 3.2200000000000003e-05,
|
| 799 |
+
"loss": 0.6019,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5066666666666667,
|
| 804 |
+
"grad_norm": 2.984369993209839,
|
| 805 |
+
"learning_rate": 3.191428571428571e-05,
|
| 806 |
+
"loss": 0.8876,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5111111111111111,
|
| 811 |
+
"grad_norm": 2.645580291748047,
|
| 812 |
+
"learning_rate": 3.162857142857143e-05,
|
| 813 |
+
"loss": 0.6198,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5155555555555555,
|
| 818 |
+
"grad_norm": 6.525484085083008,
|
| 819 |
+
"learning_rate": 3.1342857142857145e-05,
|
| 820 |
+
"loss": 0.7378,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.52,
|
| 825 |
+
"grad_norm": 2.520108938217163,
|
| 826 |
+
"learning_rate": 3.1057142857142854e-05,
|
| 827 |
+
"loss": 0.6144,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5244444444444445,
|
| 832 |
+
"grad_norm": 1.4671144485473633,
|
| 833 |
+
"learning_rate": 3.077142857142857e-05,
|
| 834 |
+
"loss": 0.5624,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5288888888888889,
|
| 839 |
+
"grad_norm": 1.6521360874176025,
|
| 840 |
+
"learning_rate": 3.048571428571429e-05,
|
| 841 |
+
"loss": 0.8754,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5333333333333333,
|
| 846 |
+
"grad_norm": 1.7824636697769165,
|
| 847 |
+
"learning_rate": 3.02e-05,
|
| 848 |
+
"loss": 0.6161,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5377777777777778,
|
| 853 |
+
"grad_norm": 3.1892054080963135,
|
| 854 |
+
"learning_rate": 2.9914285714285718e-05,
|
| 855 |
+
"loss": 0.6746,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5422222222222223,
|
| 860 |
+
"grad_norm": 2.471684217453003,
|
| 861 |
+
"learning_rate": 2.9628571428571428e-05,
|
| 862 |
+
"loss": 0.7047,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5466666666666666,
|
| 867 |
+
"grad_norm": 1.1938486099243164,
|
| 868 |
+
"learning_rate": 2.9342857142857144e-05,
|
| 869 |
+
"loss": 0.7613,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5511111111111111,
|
| 874 |
+
"grad_norm": 4.988212585449219,
|
| 875 |
+
"learning_rate": 2.905714285714286e-05,
|
| 876 |
+
"loss": 0.7503,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5555555555555556,
|
| 881 |
+
"grad_norm": 6.780579566955566,
|
| 882 |
+
"learning_rate": 2.8771428571428572e-05,
|
| 883 |
+
"loss": 0.5375,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.56,
|
| 888 |
+
"grad_norm": 2.5735678672790527,
|
| 889 |
+
"learning_rate": 2.848571428571429e-05,
|
| 890 |
+
"loss": 0.703,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5644444444444444,
|
| 895 |
+
"grad_norm": 3.509777069091797,
|
| 896 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 897 |
+
"loss": 0.5273,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5688888888888889,
|
| 902 |
+
"grad_norm": 1.5865542888641357,
|
| 903 |
+
"learning_rate": 2.7914285714285714e-05,
|
| 904 |
+
"loss": 0.4821,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5733333333333334,
|
| 909 |
+
"grad_norm": 1.2859346866607666,
|
| 910 |
+
"learning_rate": 2.762857142857143e-05,
|
| 911 |
+
"loss": 0.6347,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5777777777777777,
|
| 916 |
+
"grad_norm": 2.0483293533325195,
|
| 917 |
+
"learning_rate": 2.7342857142857142e-05,
|
| 918 |
+
"loss": 0.4798,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5822222222222222,
|
| 923 |
+
"grad_norm": 1.2751628160476685,
|
| 924 |
+
"learning_rate": 2.705714285714286e-05,
|
| 925 |
+
"loss": 0.4283,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.5866666666666667,
|
| 930 |
+
"grad_norm": 1.7461509704589844,
|
| 931 |
+
"learning_rate": 2.6771428571428575e-05,
|
| 932 |
+
"loss": 0.577,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5911111111111111,
|
| 937 |
+
"grad_norm": 2.4847190380096436,
|
| 938 |
+
"learning_rate": 2.6485714285714287e-05,
|
| 939 |
+
"loss": 0.6608,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.5955555555555555,
|
| 944 |
+
"grad_norm": 7.046814441680908,
|
| 945 |
+
"learning_rate": 2.6200000000000003e-05,
|
| 946 |
+
"loss": 0.7501,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6,
|
| 951 |
+
"grad_norm": 1.8862992525100708,
|
| 952 |
+
"learning_rate": 2.5914285714285713e-05,
|
| 953 |
+
"loss": 0.5347,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6044444444444445,
|
| 958 |
+
"grad_norm": 1.941525936126709,
|
| 959 |
+
"learning_rate": 2.562857142857143e-05,
|
| 960 |
+
"loss": 0.6533,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6088888888888889,
|
| 965 |
+
"grad_norm": 1.9246207475662231,
|
| 966 |
+
"learning_rate": 2.5342857142857145e-05,
|
| 967 |
+
"loss": 0.4619,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6133333333333333,
|
| 972 |
+
"grad_norm": 2.3284366130828857,
|
| 973 |
+
"learning_rate": 2.5057142857142857e-05,
|
| 974 |
+
"loss": 0.5442,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6177777777777778,
|
| 979 |
+
"grad_norm": 3.2495412826538086,
|
| 980 |
+
"learning_rate": 2.4771428571428573e-05,
|
| 981 |
+
"loss": 0.5538,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6222222222222222,
|
| 986 |
+
"grad_norm": 1.9646495580673218,
|
| 987 |
+
"learning_rate": 2.4485714285714286e-05,
|
| 988 |
+
"loss": 0.6764,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6266666666666667,
|
| 993 |
+
"grad_norm": 2.3741135597229004,
|
| 994 |
+
"learning_rate": 2.4200000000000002e-05,
|
| 995 |
+
"loss": 0.4923,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6311111111111111,
|
| 1000 |
+
"grad_norm": 3.175323486328125,
|
| 1001 |
+
"learning_rate": 2.3914285714285715e-05,
|
| 1002 |
+
"loss": 0.5318,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6355555555555555,
|
| 1007 |
+
"grad_norm": 4.018131732940674,
|
| 1008 |
+
"learning_rate": 2.362857142857143e-05,
|
| 1009 |
+
"loss": 0.6042,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.64,
|
| 1014 |
+
"grad_norm": 5.065487384796143,
|
| 1015 |
+
"learning_rate": 2.3342857142857143e-05,
|
| 1016 |
+
"loss": 0.4944,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6444444444444445,
|
| 1021 |
+
"grad_norm": 4.733597278594971,
|
| 1022 |
+
"learning_rate": 2.3057142857142856e-05,
|
| 1023 |
+
"loss": 0.5209,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6488888888888888,
|
| 1028 |
+
"grad_norm": 2.8453125953674316,
|
| 1029 |
+
"learning_rate": 2.2771428571428572e-05,
|
| 1030 |
+
"loss": 0.6981,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6533333333333333,
|
| 1035 |
+
"grad_norm": 5.391908168792725,
|
| 1036 |
+
"learning_rate": 2.2485714285714288e-05,
|
| 1037 |
+
"loss": 0.6173,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6577777777777778,
|
| 1042 |
+
"grad_norm": 3.4642038345336914,
|
| 1043 |
+
"learning_rate": 2.22e-05,
|
| 1044 |
+
"loss": 0.5644,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6622222222222223,
|
| 1049 |
+
"grad_norm": 5.350740909576416,
|
| 1050 |
+
"learning_rate": 2.1914285714285714e-05,
|
| 1051 |
+
"loss": 0.6647,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6666666666666666,
|
| 1056 |
+
"grad_norm": 1.7532992362976074,
|
| 1057 |
+
"learning_rate": 2.162857142857143e-05,
|
| 1058 |
+
"loss": 0.5771,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6711111111111111,
|
| 1063 |
+
"grad_norm": 1.6923083066940308,
|
| 1064 |
+
"learning_rate": 2.1342857142857146e-05,
|
| 1065 |
+
"loss": 0.4541,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6755555555555556,
|
| 1070 |
+
"grad_norm": 3.4142796993255615,
|
| 1071 |
+
"learning_rate": 2.105714285714286e-05,
|
| 1072 |
+
"loss": 0.6353,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.68,
|
| 1077 |
+
"grad_norm": 1.2692922353744507,
|
| 1078 |
+
"learning_rate": 2.077142857142857e-05,
|
| 1079 |
+
"loss": 0.6471,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6844444444444444,
|
| 1084 |
+
"grad_norm": 6.867006778717041,
|
| 1085 |
+
"learning_rate": 2.0485714285714287e-05,
|
| 1086 |
+
"loss": 0.5668,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6888888888888889,
|
| 1091 |
+
"grad_norm": 1.1940428018569946,
|
| 1092 |
+
"learning_rate": 2.0200000000000003e-05,
|
| 1093 |
+
"loss": 0.7113,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.6933333333333334,
|
| 1098 |
+
"grad_norm": 0.9745553731918335,
|
| 1099 |
+
"learning_rate": 1.9914285714285716e-05,
|
| 1100 |
+
"loss": 0.6865,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6977777777777778,
|
| 1105 |
+
"grad_norm": 1.4725788831710815,
|
| 1106 |
+
"learning_rate": 1.962857142857143e-05,
|
| 1107 |
+
"loss": 0.7809,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7022222222222222,
|
| 1112 |
+
"grad_norm": 2.4500861167907715,
|
| 1113 |
+
"learning_rate": 1.9342857142857144e-05,
|
| 1114 |
+
"loss": 0.5468,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7066666666666667,
|
| 1119 |
+
"grad_norm": 13.177860260009766,
|
| 1120 |
+
"learning_rate": 1.9057142857142857e-05,
|
| 1121 |
+
"loss": 0.5427,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7111111111111111,
|
| 1126 |
+
"grad_norm": 5.718009948730469,
|
| 1127 |
+
"learning_rate": 1.8771428571428573e-05,
|
| 1128 |
+
"loss": 0.6003,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7155555555555555,
|
| 1133 |
+
"grad_norm": 2.4186694622039795,
|
| 1134 |
+
"learning_rate": 1.8485714285714286e-05,
|
| 1135 |
+
"loss": 0.4843,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.72,
|
| 1140 |
+
"grad_norm": 1.150259256362915,
|
| 1141 |
+
"learning_rate": 1.8200000000000002e-05,
|
| 1142 |
+
"loss": 0.4339,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7244444444444444,
|
| 1147 |
+
"grad_norm": 2.5581448078155518,
|
| 1148 |
+
"learning_rate": 1.7914285714285715e-05,
|
| 1149 |
+
"loss": 0.7765,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7288888888888889,
|
| 1154 |
+
"grad_norm": 2.4859399795532227,
|
| 1155 |
+
"learning_rate": 1.762857142857143e-05,
|
| 1156 |
+
"loss": 0.5869,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7333333333333333,
|
| 1161 |
+
"grad_norm": 1.6887503862380981,
|
| 1162 |
+
"learning_rate": 1.7342857142857143e-05,
|
| 1163 |
+
"loss": 0.4651,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7377777777777778,
|
| 1168 |
+
"grad_norm": 2.0939149856567383,
|
| 1169 |
+
"learning_rate": 1.7057142857142856e-05,
|
| 1170 |
+
"loss": 0.7603,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7422222222222222,
|
| 1175 |
+
"grad_norm": 1.9502744674682617,
|
| 1176 |
+
"learning_rate": 1.6771428571428572e-05,
|
| 1177 |
+
"loss": 0.5475,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7466666666666667,
|
| 1182 |
+
"grad_norm": 0.8679394721984863,
|
| 1183 |
+
"learning_rate": 1.6485714285714288e-05,
|
| 1184 |
+
"loss": 0.4752,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7511111111111111,
|
| 1189 |
+
"grad_norm": 1.2583119869232178,
|
| 1190 |
+
"learning_rate": 1.62e-05,
|
| 1191 |
+
"loss": 0.5677,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7555555555555555,
|
| 1196 |
+
"grad_norm": 2.252943754196167,
|
| 1197 |
+
"learning_rate": 1.5914285714285713e-05,
|
| 1198 |
+
"loss": 0.4604,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.76,
|
| 1203 |
+
"grad_norm": 1.150745153427124,
|
| 1204 |
+
"learning_rate": 1.562857142857143e-05,
|
| 1205 |
+
"loss": 0.5713,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7644444444444445,
|
| 1210 |
+
"grad_norm": 1.7483420372009277,
|
| 1211 |
+
"learning_rate": 1.5342857142857146e-05,
|
| 1212 |
+
"loss": 0.5989,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7688888888888888,
|
| 1217 |
+
"grad_norm": 0.8522917628288269,
|
| 1218 |
+
"learning_rate": 1.5057142857142858e-05,
|
| 1219 |
+
"loss": 0.5211,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7733333333333333,
|
| 1224 |
+
"grad_norm": 2.067723035812378,
|
| 1225 |
+
"learning_rate": 1.4771428571428573e-05,
|
| 1226 |
+
"loss": 0.6904,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7777777777777778,
|
| 1231 |
+
"grad_norm": 1.3494257926940918,
|
| 1232 |
+
"learning_rate": 1.4485714285714285e-05,
|
| 1233 |
+
"loss": 0.6667,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7822222222222223,
|
| 1238 |
+
"grad_norm": 1.3629013299942017,
|
| 1239 |
+
"learning_rate": 1.42e-05,
|
| 1240 |
+
"loss": 0.3367,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7866666666666666,
|
| 1245 |
+
"grad_norm": 3.2202422618865967,
|
| 1246 |
+
"learning_rate": 1.3914285714285716e-05,
|
| 1247 |
+
"loss": 0.6033,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.7911111111111111,
|
| 1252 |
+
"grad_norm": 1.038692593574524,
|
| 1253 |
+
"learning_rate": 1.362857142857143e-05,
|
| 1254 |
+
"loss": 0.5305,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.7955555555555556,
|
| 1259 |
+
"grad_norm": 2.57888126373291,
|
| 1260 |
+
"learning_rate": 1.3342857142857143e-05,
|
| 1261 |
+
"loss": 0.5989,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8,
|
| 1266 |
+
"grad_norm": 1.118715524673462,
|
| 1267 |
+
"learning_rate": 1.3057142857142857e-05,
|
| 1268 |
+
"loss": 0.4963,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8044444444444444,
|
| 1273 |
+
"grad_norm": 2.586069107055664,
|
| 1274 |
+
"learning_rate": 1.2771428571428573e-05,
|
| 1275 |
+
"loss": 0.6829,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8088888888888889,
|
| 1280 |
+
"grad_norm": 2.27518630027771,
|
| 1281 |
+
"learning_rate": 1.2485714285714287e-05,
|
| 1282 |
+
"loss": 0.7121,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8133333333333334,
|
| 1287 |
+
"grad_norm": 1.1266392469406128,
|
| 1288 |
+
"learning_rate": 1.22e-05,
|
| 1289 |
+
"loss": 0.5293,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8177777777777778,
|
| 1294 |
+
"grad_norm": 1.4908055067062378,
|
| 1295 |
+
"learning_rate": 1.1914285714285716e-05,
|
| 1296 |
+
"loss": 0.5562,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8222222222222222,
|
| 1301 |
+
"grad_norm": 1.4283602237701416,
|
| 1302 |
+
"learning_rate": 1.1628571428571429e-05,
|
| 1303 |
+
"loss": 0.4831,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8266666666666667,
|
| 1308 |
+
"grad_norm": 1.0552829504013062,
|
| 1309 |
+
"learning_rate": 1.1342857142857143e-05,
|
| 1310 |
+
"loss": 0.5761,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8311111111111111,
|
| 1315 |
+
"grad_norm": 6.45361852645874,
|
| 1316 |
+
"learning_rate": 1.1057142857142858e-05,
|
| 1317 |
+
"loss": 0.6874,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8355555555555556,
|
| 1322 |
+
"grad_norm": 1.207909345626831,
|
| 1323 |
+
"learning_rate": 1.0771428571428572e-05,
|
| 1324 |
+
"loss": 0.6289,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.84,
|
| 1329 |
+
"grad_norm": 3.6151106357574463,
|
| 1330 |
+
"learning_rate": 1.0485714285714286e-05,
|
| 1331 |
+
"loss": 0.78,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8444444444444444,
|
| 1336 |
+
"grad_norm": 2.560347318649292,
|
| 1337 |
+
"learning_rate": 1.02e-05,
|
| 1338 |
+
"loss": 0.7657,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8488888888888889,
|
| 1343 |
+
"grad_norm": 1.1826066970825195,
|
| 1344 |
+
"learning_rate": 9.914285714285715e-06,
|
| 1345 |
+
"loss": 0.5419,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8533333333333334,
|
| 1350 |
+
"grad_norm": 2.4970545768737793,
|
| 1351 |
+
"learning_rate": 9.628571428571428e-06,
|
| 1352 |
+
"loss": 0.5137,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8577777777777778,
|
| 1357 |
+
"grad_norm": 1.6849817037582397,
|
| 1358 |
+
"learning_rate": 9.342857142857144e-06,
|
| 1359 |
+
"loss": 0.4476,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.8622222222222222,
|
| 1364 |
+
"grad_norm": 3.5557351112365723,
|
| 1365 |
+
"learning_rate": 9.057142857142856e-06,
|
| 1366 |
+
"loss": 0.6422,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8666666666666667,
|
| 1371 |
+
"grad_norm": 1.7327756881713867,
|
| 1372 |
+
"learning_rate": 8.771428571428572e-06,
|
| 1373 |
+
"loss": 0.656,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8711111111111111,
|
| 1378 |
+
"grad_norm": 1.3222990036010742,
|
| 1379 |
+
"learning_rate": 8.485714285714285e-06,
|
| 1380 |
+
"loss": 0.6862,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8755555555555555,
|
| 1385 |
+
"grad_norm": 1.3732144832611084,
|
| 1386 |
+
"learning_rate": 8.200000000000001e-06,
|
| 1387 |
+
"loss": 0.5173,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.88,
|
| 1392 |
+
"grad_norm": 5.491960048675537,
|
| 1393 |
+
"learning_rate": 7.914285714285714e-06,
|
| 1394 |
+
"loss": 0.5735,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.8844444444444445,
|
| 1399 |
+
"grad_norm": 1.9830958843231201,
|
| 1400 |
+
"learning_rate": 7.628571428571429e-06,
|
| 1401 |
+
"loss": 0.4936,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8888888888888888,
|
| 1406 |
+
"grad_norm": 3.4833927154541016,
|
| 1407 |
+
"learning_rate": 7.342857142857143e-06,
|
| 1408 |
+
"loss": 0.5099,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8933333333333333,
|
| 1413 |
+
"grad_norm": 1.197811484336853,
|
| 1414 |
+
"learning_rate": 7.057142857142858e-06,
|
| 1415 |
+
"loss": 0.4711,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.8977777777777778,
|
| 1420 |
+
"grad_norm": 2.15141224861145,
|
| 1421 |
+
"learning_rate": 6.771428571428571e-06,
|
| 1422 |
+
"loss": 0.5555,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9022222222222223,
|
| 1427 |
+
"grad_norm": 1.7254974842071533,
|
| 1428 |
+
"learning_rate": 6.485714285714286e-06,
|
| 1429 |
+
"loss": 0.5582,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9066666666666666,
|
| 1434 |
+
"grad_norm": 9.579049110412598,
|
| 1435 |
+
"learning_rate": 6.2e-06,
|
| 1436 |
+
"loss": 0.4571,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9111111111111111,
|
| 1441 |
+
"grad_norm": 2.882373094558716,
|
| 1442 |
+
"learning_rate": 5.914285714285714e-06,
|
| 1443 |
+
"loss": 0.6287,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9155555555555556,
|
| 1448 |
+
"grad_norm": 5.913229942321777,
|
| 1449 |
+
"learning_rate": 5.628571428571429e-06,
|
| 1450 |
+
"loss": 0.5779,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.92,
|
| 1455 |
+
"grad_norm": 4.352343559265137,
|
| 1456 |
+
"learning_rate": 5.342857142857143e-06,
|
| 1457 |
+
"loss": 0.5565,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9244444444444444,
|
| 1462 |
+
"grad_norm": 2.8510098457336426,
|
| 1463 |
+
"learning_rate": 5.057142857142857e-06,
|
| 1464 |
+
"loss": 0.5999,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9288888888888889,
|
| 1469 |
+
"grad_norm": 2.46824049949646,
|
| 1470 |
+
"learning_rate": 4.771428571428572e-06,
|
| 1471 |
+
"loss": 0.4779,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9333333333333333,
|
| 1476 |
+
"grad_norm": 1.5886437892913818,
|
| 1477 |
+
"learning_rate": 4.485714285714286e-06,
|
| 1478 |
+
"loss": 0.5774,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9377777777777778,
|
| 1483 |
+
"grad_norm": 1.5184223651885986,
|
| 1484 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 1485 |
+
"loss": 0.4278,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9422222222222222,
|
| 1490 |
+
"grad_norm": 4.225131511688232,
|
| 1491 |
+
"learning_rate": 3.914285714285715e-06,
|
| 1492 |
+
"loss": 0.6479,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9466666666666667,
|
| 1497 |
+
"grad_norm": 2.665025234222412,
|
| 1498 |
+
"learning_rate": 3.6285714285714283e-06,
|
| 1499 |
+
"loss": 0.4907,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9511111111111111,
|
| 1504 |
+
"grad_norm": 1.4222490787506104,
|
| 1505 |
+
"learning_rate": 3.3428571428571427e-06,
|
| 1506 |
+
"loss": 0.4263,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.9555555555555556,
|
| 1511 |
+
"grad_norm": 1.8098088502883911,
|
| 1512 |
+
"learning_rate": 3.0571428571428575e-06,
|
| 1513 |
+
"loss": 0.512,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.96,
|
| 1518 |
+
"grad_norm": 1.5185695886611938,
|
| 1519 |
+
"learning_rate": 2.771428571428572e-06,
|
| 1520 |
+
"loss": 0.4707,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.9644444444444444,
|
| 1525 |
+
"grad_norm": 3.510244846343994,
|
| 1526 |
+
"learning_rate": 2.4857142857142858e-06,
|
| 1527 |
+
"loss": 0.5985,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.9688888888888889,
|
| 1532 |
+
"grad_norm": 2.4858155250549316,
|
| 1533 |
+
"learning_rate": 2.2e-06,
|
| 1534 |
+
"loss": 0.5148,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.9733333333333334,
|
| 1539 |
+
"grad_norm": 2.5503909587860107,
|
| 1540 |
+
"learning_rate": 1.9142857142857145e-06,
|
| 1541 |
+
"loss": 0.5905,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.9777777777777777,
|
| 1546 |
+
"grad_norm": 1.640555739402771,
|
| 1547 |
+
"learning_rate": 1.6285714285714286e-06,
|
| 1548 |
+
"loss": 0.4983,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.9822222222222222,
|
| 1553 |
+
"grad_norm": 3.124906539916992,
|
| 1554 |
+
"learning_rate": 1.342857142857143e-06,
|
| 1555 |
+
"loss": 0.4201,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.9866666666666667,
|
| 1560 |
+
"grad_norm": 2.2014262676239014,
|
| 1561 |
+
"learning_rate": 1.0571428571428573e-06,
|
| 1562 |
+
"loss": 0.5991,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.9911111111111112,
|
| 1567 |
+
"grad_norm": 1.412158727645874,
|
| 1568 |
+
"learning_rate": 7.714285714285715e-07,
|
| 1569 |
+
"loss": 0.5062,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.9955555555555555,
|
| 1574 |
+
"grad_norm": 2.74906325340271,
|
| 1575 |
+
"learning_rate": 4.857142857142857e-07,
|
| 1576 |
+
"loss": 0.6499,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.0,
|
| 1581 |
+
"grad_norm": 1.1791956424713135,
|
| 1582 |
+
"learning_rate": 2.0000000000000002e-07,
|
| 1583 |
+
"loss": 0.521,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
}
|
| 1586 |
+
],
|
| 1587 |
+
"logging_steps": 10,
|
| 1588 |
+
"max_steps": 2250,
|
| 1589 |
+
"num_input_tokens_seen": 0,
|
| 1590 |
+
"num_train_epochs": 1,
|
| 1591 |
+
"save_steps": 5000,
|
| 1592 |
+
"stateful_callbacks": {
|
| 1593 |
+
"TrainerControl": {
|
| 1594 |
+
"args": {
|
| 1595 |
+
"should_epoch_stop": false,
|
| 1596 |
+
"should_evaluate": false,
|
| 1597 |
+
"should_log": false,
|
| 1598 |
+
"should_save": true,
|
| 1599 |
+
"should_training_stop": true
|
| 1600 |
+
},
|
| 1601 |
+
"attributes": {}
|
| 1602 |
+
}
|
| 1603 |
+
},
|
| 1604 |
+
"total_flos": 3.20270921367552e+17,
|
| 1605 |
+
"train_batch_size": 1,
|
| 1606 |
+
"trial_name": null,
|
| 1607 |
+
"trial_params": null
|
| 1608 |
+
}
|
checkpoint-2250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cfca77605318cc6783e144ea561ebd8cbb71497d4cfd2e24060b0eeb3142707
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco-plus",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 26,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.46.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.46.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e7be3ecd6b2779ed54c53d5fbba0e115f498f10873208dfc88d3fa866cb0b10
|
| 3 |
+
size 3092603344
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "</s>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "<unk>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"cls_token": "</s>",
|
| 35 |
+
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": "<unk>",
|
| 39 |
+
"sep_token": "</s>",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"spaces_between_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cfca77605318cc6783e144ea561ebd8cbb71497d4cfd2e24060b0eeb3142707
|
| 3 |
+
size 5240
|