Upload 15 files
Browse files- .gitattributes +35 -35
- added_tokens.json +40 -0
- config.json +30 -0
- generation_config.json +10 -0
- latest +1 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +60 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +352 -0
- trainer_state.json +2082 -0
- training_args.bin +3 -0
- zero_to_fp32.py +604 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,35 @@
|
|
| 1 |
-
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|/code|>": 32014,
|
| 3 |
+
"<|/data|>": 32033,
|
| 4 |
+
"<|/inst|>": 32037,
|
| 5 |
+
"<|/query|>": 32031,
|
| 6 |
+
"<|/sys|>": 32035,
|
| 7 |
+
"<|assistant_mask|>": 32017,
|
| 8 |
+
"<|assistant|>": 32001,
|
| 9 |
+
"<|calc|>": 32012,
|
| 10 |
+
"<|code|>": 32013,
|
| 11 |
+
"<|continue|>": 32009,
|
| 12 |
+
"<|data|>": 32032,
|
| 13 |
+
"<|diff_marker|>": 32025,
|
| 14 |
+
"<|disc_sep|>": 32029,
|
| 15 |
+
"<|disc_start|>": 32028,
|
| 16 |
+
"<|disc_thread|><|query|>": 32030,
|
| 17 |
+
"<|endoftext|>": 32000,
|
| 18 |
+
"<|end|>": 32007,
|
| 19 |
+
"<|fim_middle|>": 32021,
|
| 20 |
+
"<|fim_prefix|>": 32020,
|
| 21 |
+
"<|fim_suffix|>": 32022,
|
| 22 |
+
"<|function_call|>": 32005,
|
| 23 |
+
"<|function_list|>": 32011,
|
| 24 |
+
"<|function_output|>": 32003,
|
| 25 |
+
"<|ghissue|>": 32026,
|
| 26 |
+
"<|ghreview|>": 32027,
|
| 27 |
+
"<|inst|>": 32036,
|
| 28 |
+
"<|ipynb_marker|>": 32024,
|
| 29 |
+
"<|message|>": 32019,
|
| 30 |
+
"<|meta_start|>": 32023,
|
| 31 |
+
"<|raw|>": 32008,
|
| 32 |
+
"<|resource|>": 32016,
|
| 33 |
+
"<|start|>": 32018,
|
| 34 |
+
"<|step|>": 32002,
|
| 35 |
+
"<|summary|>": 32015,
|
| 36 |
+
"<|system|>": 32006,
|
| 37 |
+
"<|sys|>": 32034,
|
| 38 |
+
"<|tag|>": 32004,
|
| 39 |
+
"<|user|>": 32010
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "avemio-digital/GRAG-PHI-3.5-MINI-4B-SFT-HESSIAN-AI",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 32000,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 3072,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"sliding_window": 2047,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.39.3",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32064
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
32000,
|
| 6 |
+
32007
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 32000,
|
| 9 |
+
"transformers_version": "4.39.3"
|
| 10 |
+
}
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step3360
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:358eb26d0132f58623b37a887551579e5acf1987ec0073b5a7124446e47eb5b0
|
| 3 |
+
size 4991370968
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2bf802d83278bbf2cda06b82e1cc7b72768690015534003a8337a8e3454624
|
| 3 |
+
size 2650821816
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7642159104
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|user|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|system|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|assistant|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|end|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"bos_token": {
|
| 33 |
+
"content": "<s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"eos_token": {
|
| 40 |
+
"content": "<|end|>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"pad_token": {
|
| 47 |
+
"content": "<|endoftext|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
},
|
| 53 |
+
"unk_token": {
|
| 54 |
+
"content": "<unk>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false
|
| 59 |
+
}
|
| 60 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,352 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|step|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|function_output|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|tag|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|function_call|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|raw|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|continue|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32011": {
|
| 118 |
+
"content": "<|function_list|>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": true,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32012": {
|
| 126 |
+
"content": "<|calc|>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": true,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"32013": {
|
| 134 |
+
"content": "<|code|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": true,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"32014": {
|
| 142 |
+
"content": "<|/code|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": true,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"32015": {
|
| 150 |
+
"content": "<|summary|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": true,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"32016": {
|
| 158 |
+
"content": "<|resource|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": true,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"32017": {
|
| 166 |
+
"content": "<|assistant_mask|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": true,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"32018": {
|
| 174 |
+
"content": "<|start|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": true,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"32019": {
|
| 182 |
+
"content": "<|message|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": true,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"32020": {
|
| 190 |
+
"content": "<|fim_prefix|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": true,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"32021": {
|
| 198 |
+
"content": "<|fim_middle|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": true,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"32022": {
|
| 206 |
+
"content": "<|fim_suffix|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": true,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
"32023": {
|
| 214 |
+
"content": "<|meta_start|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": true,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"32024": {
|
| 222 |
+
"content": "<|ipynb_marker|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": true,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"32025": {
|
| 230 |
+
"content": "<|diff_marker|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": true,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"32026": {
|
| 238 |
+
"content": "<|ghissue|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": true,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"32027": {
|
| 246 |
+
"content": "<|ghreview|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": true,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"32028": {
|
| 254 |
+
"content": "<|disc_start|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": true,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"32029": {
|
| 262 |
+
"content": "<|disc_sep|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": true,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": true
|
| 268 |
+
},
|
| 269 |
+
"32030": {
|
| 270 |
+
"content": "<|disc_thread|><|query|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": true,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"32031": {
|
| 278 |
+
"content": "<|/query|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": true,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"32032": {
|
| 286 |
+
"content": "<|data|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": true,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"32033": {
|
| 294 |
+
"content": "<|/data|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": true,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"32034": {
|
| 302 |
+
"content": "<|sys|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": true,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"32035": {
|
| 310 |
+
"content": "<|/sys|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": true,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"32036": {
|
| 318 |
+
"content": "<|inst|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": true,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"32037": {
|
| 326 |
+
"content": "<|/inst|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": true,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
}
|
| 333 |
+
},
|
| 334 |
+
"additional_special_tokens": [
|
| 335 |
+
"<|user|>",
|
| 336 |
+
"<|system|>",
|
| 337 |
+
"<|assistant|>",
|
| 338 |
+
"<|end|>"
|
| 339 |
+
],
|
| 340 |
+
"bos_token": "<s>",
|
| 341 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 342 |
+
"clean_up_tokenization_spaces": false,
|
| 343 |
+
"eos_token": "<|end|>",
|
| 344 |
+
"legacy": false,
|
| 345 |
+
"model_max_length": 131072,
|
| 346 |
+
"pad_token": "<|endoftext|>",
|
| 347 |
+
"padding_side": "left",
|
| 348 |
+
"sp_model_kwargs": {},
|
| 349 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 350 |
+
"unk_token": "<unk>",
|
| 351 |
+
"use_default_system_prompt": false
|
| 352 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2082 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.89591957421644,
|
| 5 |
+
"eval_steps": 400,
|
| 6 |
+
"global_step": 3360,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15138971023063277,
|
| 13 |
+
"grad_norm": 27.229875564575195,
|
| 14 |
+
"learning_rate": 4.7619047619047613e-08,
|
| 15 |
+
"log_odds_chosen": -0.0525120347738266,
|
| 16 |
+
"log_odds_ratio": -0.7864450216293335,
|
| 17 |
+
"logits/chosen": 1.5500602722167969,
|
| 18 |
+
"logits/rejected": 1.3292943239212036,
|
| 19 |
+
"logps/chosen": -1.191162109375,
|
| 20 |
+
"logps/rejected": -1.1635648012161255,
|
| 21 |
+
"loss": 1.6156,
|
| 22 |
+
"nll_loss": 1.46018648147583,
|
| 23 |
+
"rewards/accuracies": 0.43359375,
|
| 24 |
+
"rewards/chosen": -0.1786743402481079,
|
| 25 |
+
"rewards/margins": -0.004139607772231102,
|
| 26 |
+
"rewards/rejected": -0.17453473806381226,
|
| 27 |
+
"step": 32
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.30277942046126555,
|
| 31 |
+
"grad_norm": 27.179594039916992,
|
| 32 |
+
"learning_rate": 9.523809523809523e-08,
|
| 33 |
+
"log_odds_chosen": 0.019624141976237297,
|
| 34 |
+
"log_odds_ratio": -0.748144805431366,
|
| 35 |
+
"logits/chosen": 1.5089401006698608,
|
| 36 |
+
"logits/rejected": 1.3729290962219238,
|
| 37 |
+
"logps/chosen": -1.2469431161880493,
|
| 38 |
+
"logps/rejected": -1.26250422000885,
|
| 39 |
+
"loss": 1.5984,
|
| 40 |
+
"nll_loss": 1.5403207540512085,
|
| 41 |
+
"rewards/accuracies": 0.5078125,
|
| 42 |
+
"rewards/chosen": -0.1870414763689041,
|
| 43 |
+
"rewards/margins": 0.002334160730242729,
|
| 44 |
+
"rewards/rejected": -0.1893756240606308,
|
| 45 |
+
"step": 64
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4541691306918983,
|
| 49 |
+
"grad_norm": 25.431949615478516,
|
| 50 |
+
"learning_rate": 1.4285714285714285e-07,
|
| 51 |
+
"log_odds_chosen": -0.053292229771614075,
|
| 52 |
+
"log_odds_ratio": -0.78084397315979,
|
| 53 |
+
"logits/chosen": 1.5771101713180542,
|
| 54 |
+
"logits/rejected": 1.4359058141708374,
|
| 55 |
+
"logps/chosen": -1.20406174659729,
|
| 56 |
+
"logps/rejected": -1.1857094764709473,
|
| 57 |
+
"loss": 1.6007,
|
| 58 |
+
"nll_loss": 1.4434431791305542,
|
| 59 |
+
"rewards/accuracies": 0.421875,
|
| 60 |
+
"rewards/chosen": -0.18060927093029022,
|
| 61 |
+
"rewards/margins": -0.0027528139762580395,
|
| 62 |
+
"rewards/rejected": -0.1778564453125,
|
| 63 |
+
"step": 96
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.6055588409225311,
|
| 67 |
+
"grad_norm": 21.6727294921875,
|
| 68 |
+
"learning_rate": 1.9047619047619045e-07,
|
| 69 |
+
"log_odds_chosen": 0.05749227851629257,
|
| 70 |
+
"log_odds_ratio": -0.7303333878517151,
|
| 71 |
+
"logits/chosen": 1.468267560005188,
|
| 72 |
+
"logits/rejected": 1.4105079174041748,
|
| 73 |
+
"logps/chosen": -1.216729998588562,
|
| 74 |
+
"logps/rejected": -1.2735037803649902,
|
| 75 |
+
"loss": 1.5421,
|
| 76 |
+
"nll_loss": 1.4667391777038574,
|
| 77 |
+
"rewards/accuracies": 0.48046875,
|
| 78 |
+
"rewards/chosen": -0.18250951170921326,
|
| 79 |
+
"rewards/margins": 0.008516057394444942,
|
| 80 |
+
"rewards/rejected": -0.19102558493614197,
|
| 81 |
+
"step": 128
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.7569485511531638,
|
| 85 |
+
"grad_norm": 18.762540817260742,
|
| 86 |
+
"learning_rate": 2.3809523809523806e-07,
|
| 87 |
+
"log_odds_chosen": -0.01149587519466877,
|
| 88 |
+
"log_odds_ratio": -0.7697539329528809,
|
| 89 |
+
"logits/chosen": 1.5571284294128418,
|
| 90 |
+
"logits/rejected": 1.4197614192962646,
|
| 91 |
+
"logps/chosen": -1.1996402740478516,
|
| 92 |
+
"logps/rejected": -1.206023931503296,
|
| 93 |
+
"loss": 1.4771,
|
| 94 |
+
"nll_loss": 1.3902133703231812,
|
| 95 |
+
"rewards/accuracies": 0.4609375,
|
| 96 |
+
"rewards/chosen": -0.17994605004787445,
|
| 97 |
+
"rewards/margins": 0.000957544194534421,
|
| 98 |
+
"rewards/rejected": -0.1809035986661911,
|
| 99 |
+
"step": 160
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.9083382613837966,
|
| 103 |
+
"grad_norm": 14.901942253112793,
|
| 104 |
+
"learning_rate": 2.857142857142857e-07,
|
| 105 |
+
"log_odds_chosen": -0.0564657598733902,
|
| 106 |
+
"log_odds_ratio": -0.791755735874176,
|
| 107 |
+
"logits/chosen": 1.7110127210617065,
|
| 108 |
+
"logits/rejected": 1.559685468673706,
|
| 109 |
+
"logps/chosen": -1.201224446296692,
|
| 110 |
+
"logps/rejected": -1.1592237949371338,
|
| 111 |
+
"loss": 1.4155,
|
| 112 |
+
"nll_loss": 1.3239426612854004,
|
| 113 |
+
"rewards/accuracies": 0.50390625,
|
| 114 |
+
"rewards/chosen": -0.18018370866775513,
|
| 115 |
+
"rewards/margins": -0.00630012946203351,
|
| 116 |
+
"rewards/rejected": -0.1738835722208023,
|
| 117 |
+
"step": 192
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0597279716144294,
|
| 121 |
+
"grad_norm": 14.1319580078125,
|
| 122 |
+
"learning_rate": 3.333333333333333e-07,
|
| 123 |
+
"log_odds_chosen": -0.07105285674333572,
|
| 124 |
+
"log_odds_ratio": -0.7984029650688171,
|
| 125 |
+
"logits/chosen": 1.623414397239685,
|
| 126 |
+
"logits/rejected": 1.496307134628296,
|
| 127 |
+
"logps/chosen": -1.1715890169143677,
|
| 128 |
+
"logps/rejected": -1.1218650341033936,
|
| 129 |
+
"loss": 1.3513,
|
| 130 |
+
"nll_loss": 1.2719416618347168,
|
| 131 |
+
"rewards/accuracies": 0.46484375,
|
| 132 |
+
"rewards/chosen": -0.1757383644580841,
|
| 133 |
+
"rewards/margins": -0.007458594627678394,
|
| 134 |
+
"rewards/rejected": -0.16827978193759918,
|
| 135 |
+
"step": 224
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.2111176818450622,
|
| 139 |
+
"grad_norm": 13.425606727600098,
|
| 140 |
+
"learning_rate": 3.809523809523809e-07,
|
| 141 |
+
"log_odds_chosen": 0.10578853636980057,
|
| 142 |
+
"log_odds_ratio": -0.70930016040802,
|
| 143 |
+
"logits/chosen": 1.6068717241287231,
|
| 144 |
+
"logits/rejected": 1.3819518089294434,
|
| 145 |
+
"logps/chosen": -1.1136094331741333,
|
| 146 |
+
"logps/rejected": -1.1912662982940674,
|
| 147 |
+
"loss": 1.3252,
|
| 148 |
+
"nll_loss": 1.2232904434204102,
|
| 149 |
+
"rewards/accuracies": 0.546875,
|
| 150 |
+
"rewards/chosen": -0.16704143583774567,
|
| 151 |
+
"rewards/margins": 0.0116485096514225,
|
| 152 |
+
"rewards/rejected": -0.17868994176387787,
|
| 153 |
+
"step": 256
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.362507392075695,
|
| 157 |
+
"grad_norm": 11.342605590820312,
|
| 158 |
+
"learning_rate": 4.285714285714285e-07,
|
| 159 |
+
"log_odds_chosen": 0.13081349432468414,
|
| 160 |
+
"log_odds_ratio": -0.6838027238845825,
|
| 161 |
+
"logits/chosen": 1.4501845836639404,
|
| 162 |
+
"logits/rejected": 1.3310956954956055,
|
| 163 |
+
"logps/chosen": -1.0919809341430664,
|
| 164 |
+
"logps/rejected": -1.1673154830932617,
|
| 165 |
+
"loss": 1.2755,
|
| 166 |
+
"nll_loss": 1.1733828783035278,
|
| 167 |
+
"rewards/accuracies": 0.578125,
|
| 168 |
+
"rewards/chosen": -0.16379712522029877,
|
| 169 |
+
"rewards/margins": 0.011300182901322842,
|
| 170 |
+
"rewards/rejected": -0.1750973016023636,
|
| 171 |
+
"step": 288
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.5138971023063275,
|
| 175 |
+
"grad_norm": 12.543194770812988,
|
| 176 |
+
"learning_rate": 4.761904761904761e-07,
|
| 177 |
+
"log_odds_chosen": 0.19491538405418396,
|
| 178 |
+
"log_odds_ratio": -0.6595159769058228,
|
| 179 |
+
"logits/chosen": 1.4903298616409302,
|
| 180 |
+
"logits/rejected": 1.3049672842025757,
|
| 181 |
+
"logps/chosen": -1.0332714319229126,
|
| 182 |
+
"logps/rejected": -1.1428489685058594,
|
| 183 |
+
"loss": 1.2223,
|
| 184 |
+
"nll_loss": 1.0796581506729126,
|
| 185 |
+
"rewards/accuracies": 0.6171875,
|
| 186 |
+
"rewards/chosen": -0.15499071776866913,
|
| 187 |
+
"rewards/margins": 0.0164366252720356,
|
| 188 |
+
"rewards/rejected": -0.17142733931541443,
|
| 189 |
+
"step": 320
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.6652868125369604,
|
| 193 |
+
"grad_norm": 8.179709434509277,
|
| 194 |
+
"learning_rate": 4.999654636727764e-07,
|
| 195 |
+
"log_odds_chosen": 0.14331884682178497,
|
| 196 |
+
"log_odds_ratio": -0.6748344302177429,
|
| 197 |
+
"logits/chosen": 1.4205052852630615,
|
| 198 |
+
"logits/rejected": 1.3244390487670898,
|
| 199 |
+
"logps/chosen": -1.0807911157608032,
|
| 200 |
+
"logps/rejected": -1.159712314605713,
|
| 201 |
+
"loss": 1.1776,
|
| 202 |
+
"nll_loss": 1.0815861225128174,
|
| 203 |
+
"rewards/accuracies": 0.609375,
|
| 204 |
+
"rewards/chosen": -0.16211867332458496,
|
| 205 |
+
"rewards/margins": 0.011838208884000778,
|
| 206 |
+
"rewards/rejected": -0.17395688593387604,
|
| 207 |
+
"step": 352
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.8166765227675932,
|
| 211 |
+
"grad_norm": 9.002681732177734,
|
| 212 |
+
"learning_rate": 4.996892303047305e-07,
|
| 213 |
+
"log_odds_chosen": 0.15229541063308716,
|
| 214 |
+
"log_odds_ratio": -0.6689931154251099,
|
| 215 |
+
"logits/chosen": 1.3082184791564941,
|
| 216 |
+
"logits/rejected": 1.208222508430481,
|
| 217 |
+
"logps/chosen": -1.0531638860702515,
|
| 218 |
+
"logps/rejected": -1.1305123567581177,
|
| 219 |
+
"loss": 1.1209,
|
| 220 |
+
"nll_loss": 1.026604175567627,
|
| 221 |
+
"rewards/accuracies": 0.62890625,
|
| 222 |
+
"rewards/chosen": -0.15797458589076996,
|
| 223 |
+
"rewards/margins": 0.01160226296633482,
|
| 224 |
+
"rewards/rejected": -0.16957685351371765,
|
| 225 |
+
"step": 384
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.8923713778829097,
|
| 229 |
+
"eval_log_odds_chosen": 0.9119634628295898,
|
| 230 |
+
"eval_log_odds_ratio": -0.3477023243904114,
|
| 231 |
+
"eval_logits/chosen": 0.8482466340065002,
|
| 232 |
+
"eval_logits/rejected": 0.7518002986907959,
|
| 233 |
+
"eval_logps/chosen": -0.7484418153762817,
|
| 234 |
+
"eval_logps/rejected": -1.3053876161575317,
|
| 235 |
+
"eval_loss": 0.84984290599823,
|
| 236 |
+
"eval_nll_loss": 0.7749183773994446,
|
| 237 |
+
"eval_rewards/accuracies": 1.0,
|
| 238 |
+
"eval_rewards/chosen": -0.11226626485586166,
|
| 239 |
+
"eval_rewards/margins": 0.0835418850183487,
|
| 240 |
+
"eval_rewards/rejected": -0.19580814242362976,
|
| 241 |
+
"eval_runtime": 1.7821,
|
| 242 |
+
"eval_samples_per_second": 76.877,
|
| 243 |
+
"eval_steps_per_second": 10.101,
|
| 244 |
+
"step": 400
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.968066232998226,
|
| 248 |
+
"grad_norm": 10.631780624389648,
|
| 249 |
+
"learning_rate": 4.991370688303038e-07,
|
| 250 |
+
"log_odds_chosen": 0.20428910851478577,
|
| 251 |
+
"log_odds_ratio": -0.6562178134918213,
|
| 252 |
+
"logits/chosen": 1.2808618545532227,
|
| 253 |
+
"logits/rejected": 1.1230928897857666,
|
| 254 |
+
"logps/chosen": -1.0897853374481201,
|
| 255 |
+
"logps/rejected": -1.1929757595062256,
|
| 256 |
+
"loss": 1.0818,
|
| 257 |
+
"nll_loss": 1.0095133781433105,
|
| 258 |
+
"rewards/accuracies": 0.625,
|
| 259 |
+
"rewards/chosen": -0.16346779465675354,
|
| 260 |
+
"rewards/margins": 0.015478584915399551,
|
| 261 |
+
"rewards/rejected": -0.1789463758468628,
|
| 262 |
+
"step": 416
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.119455943228859,
|
| 266 |
+
"grad_norm": 9.022457122802734,
|
| 267 |
+
"learning_rate": 4.983095894354857e-07,
|
| 268 |
+
"log_odds_chosen": 0.22953583300113678,
|
| 269 |
+
"log_odds_ratio": -0.6313825845718384,
|
| 270 |
+
"logits/chosen": 1.349506139755249,
|
| 271 |
+
"logits/rejected": 1.1360180377960205,
|
| 272 |
+
"logps/chosen": -1.0178955793380737,
|
| 273 |
+
"logps/rejected": -1.142075538635254,
|
| 274 |
+
"loss": 1.0595,
|
| 275 |
+
"nll_loss": 0.9702749848365784,
|
| 276 |
+
"rewards/accuracies": 0.63671875,
|
| 277 |
+
"rewards/chosen": -0.15268434584140778,
|
| 278 |
+
"rewards/margins": 0.018626993522047997,
|
| 279 |
+
"rewards/rejected": -0.17131134867668152,
|
| 280 |
+
"step": 448
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.2708456534594914,
|
| 284 |
+
"grad_norm": 8.519028663635254,
|
| 285 |
+
"learning_rate": 4.972077065562821e-07,
|
| 286 |
+
"log_odds_chosen": 0.20490483939647675,
|
| 287 |
+
"log_odds_ratio": -0.6597353219985962,
|
| 288 |
+
"logits/chosen": 1.2364730834960938,
|
| 289 |
+
"logits/rejected": 1.1246590614318848,
|
| 290 |
+
"logps/chosen": -1.0860800743103027,
|
| 291 |
+
"logps/rejected": -1.1871649026870728,
|
| 292 |
+
"loss": 1.0455,
|
| 293 |
+
"nll_loss": 0.9942155480384827,
|
| 294 |
+
"rewards/accuracies": 0.65625,
|
| 295 |
+
"rewards/chosen": -0.16291199624538422,
|
| 296 |
+
"rewards/margins": 0.015162724070250988,
|
| 297 |
+
"rewards/rejected": -0.17807474732398987,
|
| 298 |
+
"step": 480
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.4222353636901244,
|
| 302 |
+
"grad_norm": 7.702695369720459,
|
| 303 |
+
"learning_rate": 4.958326378681848e-07,
|
| 304 |
+
"log_odds_chosen": 0.3035791516304016,
|
| 305 |
+
"log_odds_ratio": -0.6072664260864258,
|
| 306 |
+
"logits/chosen": 1.2193742990493774,
|
| 307 |
+
"logits/rejected": 1.0568186044692993,
|
| 308 |
+
"logps/chosen": -1.029651165008545,
|
| 309 |
+
"logps/rejected": -1.1974754333496094,
|
| 310 |
+
"loss": 1.031,
|
| 311 |
+
"nll_loss": 0.9461196660995483,
|
| 312 |
+
"rewards/accuracies": 0.7109375,
|
| 313 |
+
"rewards/chosen": -0.15444767475128174,
|
| 314 |
+
"rewards/margins": 0.02517363429069519,
|
| 315 |
+
"rewards/rejected": -0.17962132394313812,
|
| 316 |
+
"step": 512
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.573625073920757,
|
| 320 |
+
"grad_norm": 8.201448440551758,
|
| 321 |
+
"learning_rate": 4.941859029405353e-07,
|
| 322 |
+
"log_odds_chosen": 0.35751351714134216,
|
| 323 |
+
"log_odds_ratio": -0.5834794044494629,
|
| 324 |
+
"logits/chosen": 1.2276177406311035,
|
| 325 |
+
"logits/rejected": 1.0265512466430664,
|
| 326 |
+
"logps/chosen": -1.0028650760650635,
|
| 327 |
+
"logps/rejected": -1.1897025108337402,
|
| 328 |
+
"loss": 1.0218,
|
| 329 |
+
"nll_loss": 0.9072933793067932,
|
| 330 |
+
"rewards/accuracies": 0.73828125,
|
| 331 |
+
"rewards/chosen": -0.15042978525161743,
|
| 332 |
+
"rewards/margins": 0.028025589883327484,
|
| 333 |
+
"rewards/rejected": -0.17845536768436432,
|
| 334 |
+
"step": 544
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.72501478415139,
|
| 338 |
+
"grad_norm": 7.634998798370361,
|
| 339 |
+
"learning_rate": 4.922693215572695e-07,
|
| 340 |
+
"log_odds_chosen": 0.45870620012283325,
|
| 341 |
+
"log_odds_ratio": -0.54433274269104,
|
| 342 |
+
"logits/chosen": 1.1980278491973877,
|
| 343 |
+
"logits/rejected": 1.0682458877563477,
|
| 344 |
+
"logps/chosen": -0.978523313999176,
|
| 345 |
+
"logps/rejected": -1.243023157119751,
|
| 346 |
+
"loss": 0.9966,
|
| 347 |
+
"nll_loss": 0.921144962310791,
|
| 348 |
+
"rewards/accuracies": 0.7578125,
|
| 349 |
+
"rewards/chosen": -0.14677852392196655,
|
| 350 |
+
"rewards/margins": 0.03967496007680893,
|
| 351 |
+
"rewards/rejected": -0.1864534616470337,
|
| 352 |
+
"step": 576
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.8764044943820224,
|
| 356 |
+
"grad_norm": 7.217565059661865,
|
| 357 |
+
"learning_rate": 4.900850117058999e-07,
|
| 358 |
+
"log_odds_chosen": 0.47186481952667236,
|
| 359 |
+
"log_odds_ratio": -0.5484339594841003,
|
| 360 |
+
"logits/chosen": 1.152608871459961,
|
| 361 |
+
"logits/rejected": 1.015822172164917,
|
| 362 |
+
"logps/chosen": -1.01084566116333,
|
| 363 |
+
"logps/rejected": -1.277451992034912,
|
| 364 |
+
"loss": 0.9987,
|
| 365 |
+
"nll_loss": 0.9013168215751648,
|
| 366 |
+
"rewards/accuracies": 0.7421875,
|
| 367 |
+
"rewards/chosen": -0.1516268402338028,
|
| 368 |
+
"rewards/margins": 0.03999098762869835,
|
| 369 |
+
"rewards/rejected": -0.19161783158779144,
|
| 370 |
+
"step": 608
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.0277942046126554,
|
| 374 |
+
"grad_norm": 6.927852630615234,
|
| 375 |
+
"learning_rate": 4.876353872369572e-07,
|
| 376 |
+
"log_odds_chosen": 0.48829925060272217,
|
| 377 |
+
"log_odds_ratio": -0.5393761396408081,
|
| 378 |
+
"logits/chosen": 1.0784587860107422,
|
| 379 |
+
"logits/rejected": 0.9411880970001221,
|
| 380 |
+
"logps/chosen": -1.0088391304016113,
|
| 381 |
+
"logps/rejected": -1.271460771560669,
|
| 382 |
+
"loss": 0.9837,
|
| 383 |
+
"nll_loss": 0.9265193343162537,
|
| 384 |
+
"rewards/accuracies": 0.765625,
|
| 385 |
+
"rewards/chosen": -0.15132588148117065,
|
| 386 |
+
"rewards/margins": 0.039393242448568344,
|
| 387 |
+
"rewards/rejected": -0.1907191127538681,
|
| 388 |
+
"step": 640
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.179183914843288,
|
| 392 |
+
"grad_norm": 6.685938358306885,
|
| 393 |
+
"learning_rate": 4.849231551964771e-07,
|
| 394 |
+
"log_odds_chosen": 0.562548041343689,
|
| 395 |
+
"log_odds_ratio": -0.5139177441596985,
|
| 396 |
+
"logits/chosen": 1.1162034273147583,
|
| 397 |
+
"logits/rejected": 0.927276611328125,
|
| 398 |
+
"logps/chosen": -0.9777481555938721,
|
| 399 |
+
"logps/rejected": -1.3050942420959473,
|
| 400 |
+
"loss": 0.9845,
|
| 401 |
+
"nll_loss": 0.8839849233627319,
|
| 402 |
+
"rewards/accuracies": 0.78125,
|
| 403 |
+
"rewards/chosen": -0.14666223526000977,
|
| 404 |
+
"rewards/margins": 0.04910193011164665,
|
| 405 |
+
"rewards/rejected": -0.19576415419578552,
|
| 406 |
+
"step": 672
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 3.330573625073921,
|
| 410 |
+
"grad_norm": 5.24590539932251,
|
| 411 |
+
"learning_rate": 4.819513128344813e-07,
|
| 412 |
+
"log_odds_chosen": 0.4602447748184204,
|
| 413 |
+
"log_odds_ratio": -0.5505639314651489,
|
| 414 |
+
"logits/chosen": 1.1351033449172974,
|
| 415 |
+
"logits/rejected": 0.9407525062561035,
|
| 416 |
+
"logps/chosen": -0.9991594552993774,
|
| 417 |
+
"logps/rejected": -1.2416499853134155,
|
| 418 |
+
"loss": 0.9658,
|
| 419 |
+
"nll_loss": 0.8639576435089111,
|
| 420 |
+
"rewards/accuracies": 0.75,
|
| 421 |
+
"rewards/chosen": -0.14987392723560333,
|
| 422 |
+
"rewards/margins": 0.036373574286699295,
|
| 423 |
+
"rewards/rejected": -0.18624748289585114,
|
| 424 |
+
"step": 704
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.4819633353045534,
|
| 428 |
+
"grad_norm": 6.936483860015869,
|
| 429 |
+
"learning_rate": 4.787231442927586e-07,
|
| 430 |
+
"log_odds_chosen": 0.5815439820289612,
|
| 431 |
+
"log_odds_ratio": -0.5048896074295044,
|
| 432 |
+
"logits/chosen": 1.0991628170013428,
|
| 433 |
+
"logits/rejected": 0.8964717984199524,
|
| 434 |
+
"logps/chosen": -0.9201152920722961,
|
| 435 |
+
"logps/rejected": -1.242402195930481,
|
| 436 |
+
"loss": 0.9681,
|
| 437 |
+
"nll_loss": 0.8501954674720764,
|
| 438 |
+
"rewards/accuracies": 0.7890625,
|
| 439 |
+
"rewards/chosen": -0.13801729679107666,
|
| 440 |
+
"rewards/margins": 0.04834304004907608,
|
| 441 |
+
"rewards/rejected": -0.18636034429073334,
|
| 442 |
+
"step": 736
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.6333530455351863,
|
| 446 |
+
"grad_norm": 6.671252250671387,
|
| 447 |
+
"learning_rate": 4.752422169756047e-07,
|
| 448 |
+
"log_odds_chosen": 0.494718998670578,
|
| 449 |
+
"log_odds_ratio": -0.5431851148605347,
|
| 450 |
+
"logits/chosen": 1.1249089241027832,
|
| 451 |
+
"logits/rejected": 1.0157999992370605,
|
| 452 |
+
"logps/chosen": -1.0117340087890625,
|
| 453 |
+
"logps/rejected": -1.293691635131836,
|
| 454 |
+
"loss": 0.978,
|
| 455 |
+
"nll_loss": 0.9269427061080933,
|
| 456 |
+
"rewards/accuracies": 0.7578125,
|
| 457 |
+
"rewards/chosen": -0.15176010131835938,
|
| 458 |
+
"rewards/margins": 0.042293645441532135,
|
| 459 |
+
"rewards/rejected": -0.1940537393093109,
|
| 460 |
+
"step": 768
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.7847427557658193,
|
| 464 |
+
"grad_norm": 7.028476715087891,
|
| 465 |
+
"learning_rate": 4.715123776075336e-07,
|
| 466 |
+
"log_odds_chosen": 0.5061647891998291,
|
| 467 |
+
"log_odds_ratio": -0.5440715551376343,
|
| 468 |
+
"logits/chosen": 1.0956813097000122,
|
| 469 |
+
"logits/rejected": 0.9653363823890686,
|
| 470 |
+
"logps/chosen": -1.0257270336151123,
|
| 471 |
+
"logps/rejected": -1.3192400932312012,
|
| 472 |
+
"loss": 0.9528,
|
| 473 |
+
"nll_loss": 0.8593652844429016,
|
| 474 |
+
"rewards/accuracies": 0.75390625,
|
| 475 |
+
"rewards/chosen": -0.15385906398296356,
|
| 476 |
+
"rewards/margins": 0.044026970863342285,
|
| 477 |
+
"rewards/rejected": -0.19788604974746704,
|
| 478 |
+
"step": 800
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.7847427557658193,
|
| 482 |
+
"eval_log_odds_chosen": 1.0081945657730103,
|
| 483 |
+
"eval_log_odds_ratio": -0.3223256468772888,
|
| 484 |
+
"eval_logits/chosen": 0.7514240145683289,
|
| 485 |
+
"eval_logits/rejected": 0.6671679615974426,
|
| 486 |
+
"eval_logps/chosen": -0.7009862065315247,
|
| 487 |
+
"eval_logps/rejected": -1.2981789112091064,
|
| 488 |
+
"eval_loss": 0.7884585857391357,
|
| 489 |
+
"eval_nll_loss": 0.7162714600563049,
|
| 490 |
+
"eval_rewards/accuracies": 1.0,
|
| 491 |
+
"eval_rewards/chosen": -0.10514792799949646,
|
| 492 |
+
"eval_rewards/margins": 0.08957889676094055,
|
| 493 |
+
"eval_rewards/rejected": -0.1947268396615982,
|
| 494 |
+
"eval_runtime": 1.7846,
|
| 495 |
+
"eval_samples_per_second": 76.767,
|
| 496 |
+
"eval_steps_per_second": 10.086,
|
| 497 |
+
"step": 800
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.936132465996452,
|
| 501 |
+
"grad_norm": 6.8125834465026855,
|
| 502 |
+
"learning_rate": 4.675377479823153e-07,
|
| 503 |
+
"log_odds_chosen": 0.6920242309570312,
|
| 504 |
+
"log_odds_ratio": -0.4726037383079529,
|
| 505 |
+
"logits/chosen": 1.0377426147460938,
|
| 506 |
+
"logits/rejected": 0.9017472863197327,
|
| 507 |
+
"logps/chosen": -0.922009289264679,
|
| 508 |
+
"logps/rejected": -1.3119571208953857,
|
| 509 |
+
"loss": 0.9638,
|
| 510 |
+
"nll_loss": 0.8638713359832764,
|
| 511 |
+
"rewards/accuracies": 0.82421875,
|
| 512 |
+
"rewards/chosen": -0.13830138742923737,
|
| 513 |
+
"rewards/margins": 0.05849217250943184,
|
| 514 |
+
"rewards/rejected": -0.1967935562133789,
|
| 515 |
+
"step": 832
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.087522176227084,
|
| 519 |
+
"grad_norm": 6.372574806213379,
|
| 520 |
+
"learning_rate": 4.6332272040803887e-07,
|
| 521 |
+
"log_odds_chosen": 0.6877175569534302,
|
| 522 |
+
"log_odds_ratio": -0.46182751655578613,
|
| 523 |
+
"logits/chosen": 1.1110641956329346,
|
| 524 |
+
"logits/rejected": 0.9074443578720093,
|
| 525 |
+
"logps/chosen": -0.9194135069847107,
|
| 526 |
+
"logps/rejected": -1.3282839059829712,
|
| 527 |
+
"loss": 0.9604,
|
| 528 |
+
"nll_loss": 0.8556405901908875,
|
| 529 |
+
"rewards/accuracies": 0.83203125,
|
| 530 |
+
"rewards/chosen": -0.13791203498840332,
|
| 531 |
+
"rewards/margins": 0.06133056432008743,
|
| 532 |
+
"rewards/rejected": -0.19924262166023254,
|
| 533 |
+
"step": 864
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.238911886457718,
|
| 537 |
+
"grad_norm": 6.756438255310059,
|
| 538 |
+
"learning_rate": 4.588719528532341e-07,
|
| 539 |
+
"log_odds_chosen": 0.6642757058143616,
|
| 540 |
+
"log_odds_ratio": -0.4779506325721741,
|
| 541 |
+
"logits/chosen": 1.0594482421875,
|
| 542 |
+
"logits/rejected": 0.9946908354759216,
|
| 543 |
+
"logps/chosen": -0.965737521648407,
|
| 544 |
+
"logps/rejected": -1.359665870666504,
|
| 545 |
+
"loss": 0.954,
|
| 546 |
+
"nll_loss": 0.8865021467208862,
|
| 547 |
+
"rewards/accuracies": 0.77734375,
|
| 548 |
+
"rewards/chosen": -0.1448606252670288,
|
| 549 |
+
"rewards/margins": 0.059089258313179016,
|
| 550 |
+
"rewards/rejected": -0.20394988358020782,
|
| 551 |
+
"step": 896
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.39030159668835,
|
| 555 |
+
"grad_norm": 7.890772342681885,
|
| 556 |
+
"learning_rate": 4.5419036379941414e-07,
|
| 557 |
+
"log_odds_chosen": 0.7298649549484253,
|
| 558 |
+
"log_odds_ratio": -0.4601740837097168,
|
| 559 |
+
"logits/chosen": 1.1765400171279907,
|
| 560 |
+
"logits/rejected": 0.9228672981262207,
|
| 561 |
+
"logps/chosen": -0.9468764066696167,
|
| 562 |
+
"logps/rejected": -1.3811423778533936,
|
| 563 |
+
"loss": 0.9453,
|
| 564 |
+
"nll_loss": 0.8525615930557251,
|
| 565 |
+
"rewards/accuracies": 0.8203125,
|
| 566 |
+
"rewards/chosen": -0.1420314460992813,
|
| 567 |
+
"rewards/margins": 0.06513990461826324,
|
| 568 |
+
"rewards/rejected": -0.20717135071754456,
|
| 569 |
+
"step": 928
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.541691306918983,
|
| 573 |
+
"grad_norm": 6.184362888336182,
|
| 574 |
+
"learning_rate": 4.492831268057306e-07,
|
| 575 |
+
"log_odds_chosen": 0.7427738904953003,
|
| 576 |
+
"log_odds_ratio": -0.46771693229675293,
|
| 577 |
+
"logits/chosen": 1.0225163698196411,
|
| 578 |
+
"logits/rejected": 0.9077222943305969,
|
| 579 |
+
"logps/chosen": -0.9970439672470093,
|
| 580 |
+
"logps/rejected": -1.456943154335022,
|
| 581 |
+
"loss": 0.938,
|
| 582 |
+
"nll_loss": 0.8868236541748047,
|
| 583 |
+
"rewards/accuracies": 0.77734375,
|
| 584 |
+
"rewards/chosen": -0.14955660700798035,
|
| 585 |
+
"rewards/margins": 0.06898489594459534,
|
| 586 |
+
"rewards/rejected": -0.2185414880514145,
|
| 587 |
+
"step": 960
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 4.693081017149615,
|
| 591 |
+
"grad_norm": 6.933351993560791,
|
| 592 |
+
"learning_rate": 4.441556647917446e-07,
|
| 593 |
+
"log_odds_chosen": 0.8609212636947632,
|
| 594 |
+
"log_odds_ratio": -0.43812429904937744,
|
| 595 |
+
"logits/chosen": 1.0455502271652222,
|
| 596 |
+
"logits/rejected": 0.906272292137146,
|
| 597 |
+
"logps/chosen": -0.9208173155784607,
|
| 598 |
+
"logps/rejected": -1.457839012145996,
|
| 599 |
+
"loss": 0.9434,
|
| 600 |
+
"nll_loss": 0.8511086106300354,
|
| 601 |
+
"rewards/accuracies": 0.83203125,
|
| 602 |
+
"rewards/chosen": -0.13812260329723358,
|
| 603 |
+
"rewards/margins": 0.08055327087640762,
|
| 604 |
+
"rewards/rejected": -0.2186758816242218,
|
| 605 |
+
"step": 992
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.844470727380249,
|
| 609 |
+
"grad_norm": 6.150376796722412,
|
| 610 |
+
"learning_rate": 4.3881364404463375e-07,
|
| 611 |
+
"log_odds_chosen": 0.9446333050727844,
|
| 612 |
+
"log_odds_ratio": -0.4172128438949585,
|
| 613 |
+
"logits/chosen": 1.110432744026184,
|
| 614 |
+
"logits/rejected": 0.8510321974754333,
|
| 615 |
+
"logps/chosen": -0.9673236608505249,
|
| 616 |
+
"logps/rejected": -1.5632784366607666,
|
| 617 |
+
"loss": 0.9264,
|
| 618 |
+
"nll_loss": 0.8780388832092285,
|
| 619 |
+
"rewards/accuracies": 0.81640625,
|
| 620 |
+
"rewards/chosen": -0.14509856700897217,
|
| 621 |
+
"rewards/margins": 0.08939322084188461,
|
| 622 |
+
"rewards/rejected": -0.234491765499115,
|
| 623 |
+
"step": 1024
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 4.995860437610881,
|
| 627 |
+
"grad_norm": 5.648180961608887,
|
| 628 |
+
"learning_rate": 4.332629679574565e-07,
|
| 629 |
+
"log_odds_chosen": 0.9642012715339661,
|
| 630 |
+
"log_odds_ratio": -0.42083150148391724,
|
| 631 |
+
"logits/chosen": 1.0487498044967651,
|
| 632 |
+
"logits/rejected": 0.8362730741500854,
|
| 633 |
+
"logps/chosen": -0.9618784189224243,
|
| 634 |
+
"logps/rejected": -1.5873997211456299,
|
| 635 |
+
"loss": 0.925,
|
| 636 |
+
"nll_loss": 0.8492802381515503,
|
| 637 |
+
"rewards/accuracies": 0.8203125,
|
| 638 |
+
"rewards/chosen": -0.1442817747592926,
|
| 639 |
+
"rewards/margins": 0.09382818639278412,
|
| 640 |
+
"rewards/rejected": -0.23810997605323792,
|
| 641 |
+
"step": 1056
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 5.147250147841514,
|
| 645 |
+
"grad_norm": 6.209354400634766,
|
| 646 |
+
"learning_rate": 4.2750977050539503e-07,
|
| 647 |
+
"log_odds_chosen": 1.127962350845337,
|
| 648 |
+
"log_odds_ratio": -0.3810023367404938,
|
| 649 |
+
"logits/chosen": 0.9537469148635864,
|
| 650 |
+
"logits/rejected": 0.8183348178863525,
|
| 651 |
+
"logps/chosen": -0.9366539120674133,
|
| 652 |
+
"logps/rejected": -1.6753818988800049,
|
| 653 |
+
"loss": 0.9233,
|
| 654 |
+
"nll_loss": 0.8444766998291016,
|
| 655 |
+
"rewards/accuracies": 0.828125,
|
| 656 |
+
"rewards/chosen": -0.140498086810112,
|
| 657 |
+
"rewards/margins": 0.11080917716026306,
|
| 658 |
+
"rewards/rejected": -0.25130727887153625,
|
| 659 |
+
"step": 1088
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.298639858072146,
|
| 663 |
+
"grad_norm": 6.09550666809082,
|
| 664 |
+
"learning_rate": 4.2156040946718343e-07,
|
| 665 |
+
"log_odds_chosen": 1.1001328229904175,
|
| 666 |
+
"log_odds_ratio": -0.40834715962409973,
|
| 667 |
+
"logits/chosen": 0.9538164734840393,
|
| 668 |
+
"logits/rejected": 0.8565899133682251,
|
| 669 |
+
"logps/chosen": -0.9979989528656006,
|
| 670 |
+
"logps/rejected": -1.736957311630249,
|
| 671 |
+
"loss": 0.9264,
|
| 672 |
+
"nll_loss": 0.8773810863494873,
|
| 673 |
+
"rewards/accuracies": 0.8203125,
|
| 674 |
+
"rewards/chosen": -0.1496998369693756,
|
| 675 |
+
"rewards/margins": 0.11084374785423279,
|
| 676 |
+
"rewards/rejected": -0.2605435848236084,
|
| 677 |
+
"step": 1120
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 5.45002956830278,
|
| 681 |
+
"grad_norm": 5.165525913238525,
|
| 682 |
+
"learning_rate": 4.154214593992149e-07,
|
| 683 |
+
"log_odds_chosen": 1.4560502767562866,
|
| 684 |
+
"log_odds_ratio": -0.36019906401634216,
|
| 685 |
+
"logits/chosen": 1.0402196645736694,
|
| 686 |
+
"logits/rejected": 0.8284226655960083,
|
| 687 |
+
"logps/chosen": -0.9208565950393677,
|
| 688 |
+
"logps/rejected": -1.9513992071151733,
|
| 689 |
+
"loss": 0.9184,
|
| 690 |
+
"nll_loss": 0.8742519617080688,
|
| 691 |
+
"rewards/accuracies": 0.83984375,
|
| 692 |
+
"rewards/chosen": -0.13812850415706635,
|
| 693 |
+
"rewards/margins": 0.15458139777183533,
|
| 694 |
+
"rewards/rejected": -0.2927098870277405,
|
| 695 |
+
"step": 1152
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 5.601419278533412,
|
| 699 |
+
"grad_norm": 5.565188407897949,
|
| 700 |
+
"learning_rate": 4.090997043700909e-07,
|
| 701 |
+
"log_odds_chosen": 1.8058509826660156,
|
| 702 |
+
"log_odds_ratio": -0.34831157326698303,
|
| 703 |
+
"logits/chosen": 0.9435930252075195,
|
| 704 |
+
"logits/rejected": 0.7780628204345703,
|
| 705 |
+
"logps/chosen": -0.9824676513671875,
|
| 706 |
+
"logps/rejected": -2.3647959232330322,
|
| 707 |
+
"loss": 0.915,
|
| 708 |
+
"nll_loss": 0.9026926159858704,
|
| 709 |
+
"rewards/accuracies": 0.828125,
|
| 710 |
+
"rewards/chosen": -0.1473701447248459,
|
| 711 |
+
"rewards/margins": 0.2073492407798767,
|
| 712 |
+
"rewards/rejected": -0.3547194004058838,
|
| 713 |
+
"step": 1184
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.677114133648729,
|
| 717 |
+
"eval_log_odds_chosen": 1.515297532081604,
|
| 718 |
+
"eval_log_odds_ratio": -0.21902640163898468,
|
| 719 |
+
"eval_logits/chosen": 0.5878681540489197,
|
| 720 |
+
"eval_logits/rejected": 0.514284610748291,
|
| 721 |
+
"eval_logps/chosen": -0.6912536025047302,
|
| 722 |
+
"eval_logps/rejected": -1.6357617378234863,
|
| 723 |
+
"eval_loss": 0.7435688972473145,
|
| 724 |
+
"eval_nll_loss": 0.6848150491714478,
|
| 725 |
+
"eval_rewards/accuracies": 1.0,
|
| 726 |
+
"eval_rewards/chosen": -0.10368803888559341,
|
| 727 |
+
"eval_rewards/margins": 0.14167624711990356,
|
| 728 |
+
"eval_rewards/rejected": -0.2453642636537552,
|
| 729 |
+
"eval_runtime": 1.7754,
|
| 730 |
+
"eval_samples_per_second": 77.164,
|
| 731 |
+
"eval_steps_per_second": 10.138,
|
| 732 |
+
"step": 1200
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 5.752808988764045,
|
| 736 |
+
"grad_norm": 5.417468547821045,
|
| 737 |
+
"learning_rate": 4.0260213046364076e-07,
|
| 738 |
+
"log_odds_chosen": 2.085019111633301,
|
| 739 |
+
"log_odds_ratio": -0.31234151124954224,
|
| 740 |
+
"logits/chosen": 0.9959389567375183,
|
| 741 |
+
"logits/rejected": 0.7742877006530762,
|
| 742 |
+
"logps/chosen": -0.9441136121749878,
|
| 743 |
+
"logps/rejected": -2.5619935989379883,
|
| 744 |
+
"loss": 0.9004,
|
| 745 |
+
"nll_loss": 0.8535679578781128,
|
| 746 |
+
"rewards/accuracies": 0.8359375,
|
| 747 |
+
"rewards/chosen": -0.1416170299053192,
|
| 748 |
+
"rewards/margins": 0.24268200993537903,
|
| 749 |
+
"rewards/rejected": -0.38429906964302063,
|
| 750 |
+
"step": 1216
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 5.904198698994678,
|
| 754 |
+
"grad_norm": 7.9577178955078125,
|
| 755 |
+
"learning_rate": 3.959359180586975e-07,
|
| 756 |
+
"log_odds_chosen": 2.5801219940185547,
|
| 757 |
+
"log_odds_ratio": -0.31198883056640625,
|
| 758 |
+
"logits/chosen": 0.9304694533348083,
|
| 759 |
+
"logits/rejected": 0.7099679112434387,
|
| 760 |
+
"logps/chosen": -1.004030466079712,
|
| 761 |
+
"logps/rejected": -3.1341824531555176,
|
| 762 |
+
"loss": 0.9199,
|
| 763 |
+
"nll_loss": 0.888052225112915,
|
| 764 |
+
"rewards/accuracies": 0.8515625,
|
| 765 |
+
"rewards/chosen": -0.15060456097126007,
|
| 766 |
+
"rewards/margins": 0.3195228576660156,
|
| 767 |
+
"rewards/rejected": -0.4701274335384369,
|
| 768 |
+
"step": 1248
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 6.055588409225311,
|
| 772 |
+
"grad_norm": 7.205864906311035,
|
| 773 |
+
"learning_rate": 3.891084338941603e-07,
|
| 774 |
+
"log_odds_chosen": 2.632976770401001,
|
| 775 |
+
"log_odds_ratio": -0.33525609970092773,
|
| 776 |
+
"logits/chosen": 0.8941175937652588,
|
| 777 |
+
"logits/rejected": 0.712418794631958,
|
| 778 |
+
"logps/chosen": -0.9687196016311646,
|
| 779 |
+
"logps/rejected": -3.1566426753997803,
|
| 780 |
+
"loss": 0.9156,
|
| 781 |
+
"nll_loss": 0.8564908504486084,
|
| 782 |
+
"rewards/accuracies": 0.84765625,
|
| 783 |
+
"rewards/chosen": -0.14530794322490692,
|
| 784 |
+
"rewards/margins": 0.3281884789466858,
|
| 785 |
+
"rewards/rejected": -0.4734964370727539,
|
| 786 |
+
"step": 1280
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.206978119455943,
|
| 790 |
+
"grad_norm": 5.557631015777588,
|
| 791 |
+
"learning_rate": 3.8212722292811383e-07,
|
| 792 |
+
"log_odds_chosen": 2.9796371459960938,
|
| 793 |
+
"log_odds_ratio": -0.3066112995147705,
|
| 794 |
+
"logits/chosen": 0.9908494353294373,
|
| 795 |
+
"logits/rejected": 0.7001262903213501,
|
| 796 |
+
"logps/chosen": -0.9531494975090027,
|
| 797 |
+
"logps/rejected": -3.451514720916748,
|
| 798 |
+
"loss": 0.8945,
|
| 799 |
+
"nll_loss": 0.8682339191436768,
|
| 800 |
+
"rewards/accuracies": 0.83203125,
|
| 801 |
+
"rewards/chosen": -0.1429724246263504,
|
| 802 |
+
"rewards/margins": 0.3747548460960388,
|
| 803 |
+
"rewards/rejected": -0.517727255821228,
|
| 804 |
+
"step": 1312
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 6.358367829686576,
|
| 808 |
+
"grad_norm": 7.154934883117676,
|
| 809 |
+
"learning_rate": 3.75e-07,
|
| 810 |
+
"log_odds_chosen": 3.150144338607788,
|
| 811 |
+
"log_odds_ratio": -0.30607521533966064,
|
| 812 |
+
"logits/chosen": 0.8532112240791321,
|
| 813 |
+
"logits/rejected": 0.688872754573822,
|
| 814 |
+
"logps/chosen": -0.9391156435012817,
|
| 815 |
+
"logps/rejected": -3.6156792640686035,
|
| 816 |
+
"loss": 0.9013,
|
| 817 |
+
"nll_loss": 0.8500258922576904,
|
| 818 |
+
"rewards/accuracies": 0.84765625,
|
| 819 |
+
"rewards/chosen": -0.14086736738681793,
|
| 820 |
+
"rewards/margins": 0.40148457884788513,
|
| 821 |
+
"rewards/rejected": -0.5423519611358643,
|
| 822 |
+
"step": 1344
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 6.509757539917208,
|
| 826 |
+
"grad_norm": 5.582004070281982,
|
| 827 |
+
"learning_rate": 3.67734641305055e-07,
|
| 828 |
+
"log_odds_chosen": 3.518749475479126,
|
| 829 |
+
"log_odds_ratio": -0.26204630732536316,
|
| 830 |
+
"logits/chosen": 1.0231519937515259,
|
| 831 |
+
"logits/rejected": 0.6429997682571411,
|
| 832 |
+
"logps/chosen": -0.8629344701766968,
|
| 833 |
+
"logps/rejected": -3.8456180095672607,
|
| 834 |
+
"loss": 0.9023,
|
| 835 |
+
"nll_loss": 0.801094114780426,
|
| 836 |
+
"rewards/accuracies": 0.8671875,
|
| 837 |
+
"rewards/chosen": -0.12944017350673676,
|
| 838 |
+
"rewards/margins": 0.4474025368690491,
|
| 839 |
+
"rewards/rejected": -0.576842725276947,
|
| 840 |
+
"step": 1376
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 6.661147250147842,
|
| 844 |
+
"grad_norm": 6.333008766174316,
|
| 845 |
+
"learning_rate": 3.6033917569043597e-07,
|
| 846 |
+
"log_odds_chosen": 3.5107364654541016,
|
| 847 |
+
"log_odds_ratio": -0.25962206721305847,
|
| 848 |
+
"logits/chosen": 0.9015189409255981,
|
| 849 |
+
"logits/rejected": 0.604630172252655,
|
| 850 |
+
"logps/chosen": -0.9094609618186951,
|
| 851 |
+
"logps/rejected": -3.901463270187378,
|
| 852 |
+
"loss": 0.8982,
|
| 853 |
+
"nll_loss": 0.8305466175079346,
|
| 854 |
+
"rewards/accuracies": 0.87109375,
|
| 855 |
+
"rewards/chosen": -0.1364191472530365,
|
| 856 |
+
"rewards/margins": 0.44880032539367676,
|
| 857 |
+
"rewards/rejected": -0.5852195024490356,
|
| 858 |
+
"step": 1408
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 6.812536960378474,
|
| 862 |
+
"grad_norm": 9.112639427185059,
|
| 863 |
+
"learning_rate": 3.528217757826529e-07,
|
| 864 |
+
"log_odds_chosen": 3.822404384613037,
|
| 865 |
+
"log_odds_ratio": -0.28991812467575073,
|
| 866 |
+
"logits/chosen": 0.9384167790412903,
|
| 867 |
+
"logits/rejected": 0.6002436280250549,
|
| 868 |
+
"logps/chosen": -0.966259241104126,
|
| 869 |
+
"logps/rejected": -4.308917999267578,
|
| 870 |
+
"loss": 0.899,
|
| 871 |
+
"nll_loss": 0.8516695499420166,
|
| 872 |
+
"rewards/accuracies": 0.83203125,
|
| 873 |
+
"rewards/chosen": -0.1449388712644577,
|
| 874 |
+
"rewards/margins": 0.5013989210128784,
|
| 875 |
+
"rewards/rejected": -0.6463377475738525,
|
| 876 |
+
"step": 1440
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 6.963926670609107,
|
| 880 |
+
"grad_norm": 7.574125289916992,
|
| 881 |
+
"learning_rate": 3.4519074895611236e-07,
|
| 882 |
+
"log_odds_chosen": 3.943324327468872,
|
| 883 |
+
"log_odds_ratio": -0.26691746711730957,
|
| 884 |
+
"logits/chosen": 0.9103025197982788,
|
| 885 |
+
"logits/rejected": 0.6238164901733398,
|
| 886 |
+
"logps/chosen": -0.8985946774482727,
|
| 887 |
+
"logps/rejected": -4.343371391296387,
|
| 888 |
+
"loss": 0.8962,
|
| 889 |
+
"nll_loss": 0.8179515600204468,
|
| 890 |
+
"rewards/accuracies": 0.8984375,
|
| 891 |
+
"rewards/chosen": -0.13478921353816986,
|
| 892 |
+
"rewards/margins": 0.516716480255127,
|
| 893 |
+
"rewards/rejected": -0.651505708694458,
|
| 894 |
+
"step": 1472
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 7.11531638083974,
|
| 898 |
+
"grad_norm": 6.7364115715026855,
|
| 899 |
+
"learning_rate": 3.374545281527537e-07,
|
| 900 |
+
"log_odds_chosen": 4.374906539916992,
|
| 901 |
+
"log_odds_ratio": -0.2600148320198059,
|
| 902 |
+
"logits/chosen": 0.9600415229797363,
|
| 903 |
+
"logits/rejected": 0.6132468581199646,
|
| 904 |
+
"logps/chosen": -0.9232965707778931,
|
| 905 |
+
"logps/rejected": -4.797858715057373,
|
| 906 |
+
"loss": 0.8895,
|
| 907 |
+
"nll_loss": 0.8346379995346069,
|
| 908 |
+
"rewards/accuracies": 0.87109375,
|
| 909 |
+
"rewards/chosen": -0.13849450647830963,
|
| 910 |
+
"rewards/margins": 0.5811843872070312,
|
| 911 |
+
"rewards/rejected": -0.7196788787841797,
|
| 912 |
+
"step": 1504
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 7.266706091070373,
|
| 916 |
+
"grad_norm": 8.94677448272705,
|
| 917 |
+
"learning_rate": 3.296216625629211e-07,
|
| 918 |
+
"log_odds_chosen": 3.412320375442505,
|
| 919 |
+
"log_odds_ratio": -0.2966606616973877,
|
| 920 |
+
"logits/chosen": 0.9029962420463562,
|
| 921 |
+
"logits/rejected": 0.6578757762908936,
|
| 922 |
+
"logps/chosen": -0.9623314738273621,
|
| 923 |
+
"logps/rejected": -3.89890193939209,
|
| 924 |
+
"loss": 0.8925,
|
| 925 |
+
"nll_loss": 0.8433880805969238,
|
| 926 |
+
"rewards/accuracies": 0.8671875,
|
| 927 |
+
"rewards/chosen": -0.14434972405433655,
|
| 928 |
+
"rewards/margins": 0.4404855966567993,
|
| 929 |
+
"rewards/rejected": -0.5848353505134583,
|
| 930 |
+
"step": 1536
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 7.418095801301005,
|
| 934 |
+
"grad_norm": 5.7957353591918945,
|
| 935 |
+
"learning_rate": 3.2170080817777257e-07,
|
| 936 |
+
"log_odds_chosen": 4.052781581878662,
|
| 937 |
+
"log_odds_ratio": -0.2798649072647095,
|
| 938 |
+
"logits/chosen": 0.9068763256072998,
|
| 939 |
+
"logits/rejected": 0.6250233054161072,
|
| 940 |
+
"logps/chosen": -0.9688931107521057,
|
| 941 |
+
"logps/rejected": -4.529140472412109,
|
| 942 |
+
"loss": 0.9004,
|
| 943 |
+
"nll_loss": 0.8530284762382507,
|
| 944 |
+
"rewards/accuracies": 0.859375,
|
| 945 |
+
"rewards/chosen": -0.14533399045467377,
|
| 946 |
+
"rewards/margins": 0.534037172794342,
|
| 947 |
+
"rewards/rejected": -0.6793711185455322,
|
| 948 |
+
"step": 1568
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.569485511531638,
|
| 952 |
+
"grad_norm": 6.567281723022461,
|
| 953 |
+
"learning_rate": 3.137007182236637e-07,
|
| 954 |
+
"log_odds_chosen": 3.9496092796325684,
|
| 955 |
+
"log_odds_ratio": -0.25981855392456055,
|
| 956 |
+
"logits/chosen": 0.9131721258163452,
|
| 957 |
+
"logits/rejected": 0.6535216569900513,
|
| 958 |
+
"logps/chosen": -0.9185097813606262,
|
| 959 |
+
"logps/rejected": -4.3686933517456055,
|
| 960 |
+
"loss": 0.892,
|
| 961 |
+
"nll_loss": 0.8527241945266724,
|
| 962 |
+
"rewards/accuracies": 0.87890625,
|
| 963 |
+
"rewards/chosen": -0.1377764791250229,
|
| 964 |
+
"rewards/margins": 0.5175275206565857,
|
| 965 |
+
"rewards/rejected": -0.655303955078125,
|
| 966 |
+
"step": 1600
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 7.569485511531638,
|
| 970 |
+
"eval_log_odds_chosen": 1.6673216819763184,
|
| 971 |
+
"eval_log_odds_ratio": -0.19718672335147858,
|
| 972 |
+
"eval_logits/chosen": 0.5625311136245728,
|
| 973 |
+
"eval_logits/rejected": 0.4984322190284729,
|
| 974 |
+
"eval_logps/chosen": -0.6667929887771606,
|
| 975 |
+
"eval_logps/rejected": -1.6969513893127441,
|
| 976 |
+
"eval_loss": 0.7337117195129395,
|
| 977 |
+
"eval_nll_loss": 0.6776795387268066,
|
| 978 |
+
"eval_rewards/accuracies": 1.0,
|
| 979 |
+
"eval_rewards/chosen": -0.1000189557671547,
|
| 980 |
+
"eval_rewards/margins": 0.15452374517917633,
|
| 981 |
+
"eval_rewards/rejected": -0.2545427083969116,
|
| 982 |
+
"eval_runtime": 1.7831,
|
| 983 |
+
"eval_samples_per_second": 76.831,
|
| 984 |
+
"eval_steps_per_second": 10.095,
|
| 985 |
+
"step": 1600
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 7.720875221762271,
|
| 989 |
+
"grad_norm": 8.987198829650879,
|
| 990 |
+
"learning_rate": 3.056302334890786e-07,
|
| 991 |
+
"log_odds_chosen": 3.926710844039917,
|
| 992 |
+
"log_odds_ratio": -0.2714899480342865,
|
| 993 |
+
"logits/chosen": 0.9191571474075317,
|
| 994 |
+
"logits/rejected": 0.5953992605209351,
|
| 995 |
+
"logps/chosen": -0.9368714094161987,
|
| 996 |
+
"logps/rejected": -4.384879112243652,
|
| 997 |
+
"loss": 0.888,
|
| 998 |
+
"nll_loss": 0.8406177759170532,
|
| 999 |
+
"rewards/accuracies": 0.8671875,
|
| 1000 |
+
"rewards/chosen": -0.14053073525428772,
|
| 1001 |
+
"rewards/margins": 0.5172011852264404,
|
| 1002 |
+
"rewards/rejected": -0.6577318906784058,
|
| 1003 |
+
"step": 1632
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 7.872264931992904,
|
| 1007 |
+
"grad_norm": 5.6181230545043945,
|
| 1008 |
+
"learning_rate": 2.974982725547975e-07,
|
| 1009 |
+
"log_odds_chosen": 3.617192506790161,
|
| 1010 |
+
"log_odds_ratio": -0.32495206594467163,
|
| 1011 |
+
"logits/chosen": 0.8457501530647278,
|
| 1012 |
+
"logits/rejected": 0.6253533363342285,
|
| 1013 |
+
"logps/chosen": -1.0049875974655151,
|
| 1014 |
+
"logps/rejected": -4.156848907470703,
|
| 1015 |
+
"loss": 0.8977,
|
| 1016 |
+
"nll_loss": 0.8724310994148254,
|
| 1017 |
+
"rewards/accuracies": 0.85546875,
|
| 1018 |
+
"rewards/chosen": -0.1507481336593628,
|
| 1019 |
+
"rewards/margins": 0.47277915477752686,
|
| 1020 |
+
"rewards/rejected": -0.6235272884368896,
|
| 1021 |
+
"step": 1664
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 8.023654642223537,
|
| 1025 |
+
"grad_norm": 5.31005334854126,
|
| 1026 |
+
"learning_rate": 2.893138219380963e-07,
|
| 1027 |
+
"log_odds_chosen": 4.234038829803467,
|
| 1028 |
+
"log_odds_ratio": -0.30224624276161194,
|
| 1029 |
+
"logits/chosen": 0.922171950340271,
|
| 1030 |
+
"logits/rejected": 0.5847682952880859,
|
| 1031 |
+
"logps/chosen": -0.9686514139175415,
|
| 1032 |
+
"logps/rejected": -4.734119892120361,
|
| 1033 |
+
"loss": 0.8864,
|
| 1034 |
+
"nll_loss": 0.8605988025665283,
|
| 1035 |
+
"rewards/accuracies": 0.859375,
|
| 1036 |
+
"rewards/chosen": -0.14529772102832794,
|
| 1037 |
+
"rewards/margins": 0.5648203492164612,
|
| 1038 |
+
"rewards/rejected": -0.7101180553436279,
|
| 1039 |
+
"step": 1696
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 8.175044352454169,
|
| 1043 |
+
"grad_norm": 4.773166179656982,
|
| 1044 |
+
"learning_rate": 2.810859261618713e-07,
|
| 1045 |
+
"log_odds_chosen": 4.176573753356934,
|
| 1046 |
+
"log_odds_ratio": -0.2747136056423187,
|
| 1047 |
+
"logits/chosen": 0.9669155478477478,
|
| 1048 |
+
"logits/rejected": 0.6131560206413269,
|
| 1049 |
+
"logps/chosen": -0.941318690776825,
|
| 1050 |
+
"logps/rejected": -4.627261638641357,
|
| 1051 |
+
"loss": 0.8908,
|
| 1052 |
+
"nll_loss": 0.8429233431816101,
|
| 1053 |
+
"rewards/accuracies": 0.875,
|
| 1054 |
+
"rewards/chosen": -0.1411978155374527,
|
| 1055 |
+
"rewards/margins": 0.5528914928436279,
|
| 1056 |
+
"rewards/rejected": -0.6940892934799194,
|
| 1057 |
+
"step": 1728
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 8.326434062684802,
|
| 1061 |
+
"grad_norm": 7.928328990936279,
|
| 1062 |
+
"learning_rate": 2.728236777596621e-07,
|
| 1063 |
+
"log_odds_chosen": 4.232769012451172,
|
| 1064 |
+
"log_odds_ratio": -0.2622223496437073,
|
| 1065 |
+
"logits/chosen": 0.8704826831817627,
|
| 1066 |
+
"logits/rejected": 0.6309795379638672,
|
| 1067 |
+
"logps/chosen": -0.9345431327819824,
|
| 1068 |
+
"logps/rejected": -4.6482343673706055,
|
| 1069 |
+
"loss": 0.8856,
|
| 1070 |
+
"nll_loss": 0.849586009979248,
|
| 1071 |
+
"rewards/accuracies": 0.87109375,
|
| 1072 |
+
"rewards/chosen": -0.14018146693706512,
|
| 1073 |
+
"rewards/margins": 0.5570536851882935,
|
| 1074 |
+
"rewards/rejected": -0.6972352266311646,
|
| 1075 |
+
"step": 1760
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 8.477823772915436,
|
| 1079 |
+
"grad_norm": 7.50920295715332,
|
| 1080 |
+
"learning_rate": 2.6453620722761895e-07,
|
| 1081 |
+
"log_odds_chosen": 3.835066795349121,
|
| 1082 |
+
"log_odds_ratio": -0.2713623344898224,
|
| 1083 |
+
"logits/chosen": 0.8469685316085815,
|
| 1084 |
+
"logits/rejected": 0.5746083855628967,
|
| 1085 |
+
"logps/chosen": -0.9510048031806946,
|
| 1086 |
+
"logps/rejected": -4.287370204925537,
|
| 1087 |
+
"loss": 0.9005,
|
| 1088 |
+
"nll_loss": 0.8307653069496155,
|
| 1089 |
+
"rewards/accuracies": 0.8828125,
|
| 1090 |
+
"rewards/chosen": -0.14265072345733643,
|
| 1091 |
+
"rewards/margins": 0.5004547238349915,
|
| 1092 |
+
"rewards/rejected": -0.6431055068969727,
|
| 1093 |
+
"step": 1792
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 8.629213483146067,
|
| 1097 |
+
"grad_norm": 4.420612812042236,
|
| 1098 |
+
"learning_rate": 2.5623267293451823e-07,
|
| 1099 |
+
"log_odds_chosen": 4.375966548919678,
|
| 1100 |
+
"log_odds_ratio": -0.26864683628082275,
|
| 1101 |
+
"logits/chosen": 0.8368352055549622,
|
| 1102 |
+
"logits/rejected": 0.5574530959129333,
|
| 1103 |
+
"logps/chosen": -0.9161982536315918,
|
| 1104 |
+
"logps/rejected": -4.765947341918945,
|
| 1105 |
+
"loss": 0.8711,
|
| 1106 |
+
"nll_loss": 0.8084649443626404,
|
| 1107 |
+
"rewards/accuracies": 0.890625,
|
| 1108 |
+
"rewards/chosen": -0.13742974400520325,
|
| 1109 |
+
"rewards/margins": 0.577462375164032,
|
| 1110 |
+
"rewards/rejected": -0.7148921489715576,
|
| 1111 |
+
"step": 1824
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 8.7806031933767,
|
| 1115 |
+
"grad_norm": 5.372297286987305,
|
| 1116 |
+
"learning_rate": 2.4792225100097575e-07,
|
| 1117 |
+
"log_odds_chosen": 4.036057472229004,
|
| 1118 |
+
"log_odds_ratio": -0.28991392254829407,
|
| 1119 |
+
"logits/chosen": 0.8479549884796143,
|
| 1120 |
+
"logits/rejected": 0.6130175590515137,
|
| 1121 |
+
"logps/chosen": -0.996108889579773,
|
| 1122 |
+
"logps/rejected": -4.58188009262085,
|
| 1123 |
+
"loss": 0.8868,
|
| 1124 |
+
"nll_loss": 0.8779551386833191,
|
| 1125 |
+
"rewards/accuracies": 0.8671875,
|
| 1126 |
+
"rewards/chosen": -0.14941634237766266,
|
| 1127 |
+
"rewards/margins": 0.5378656387329102,
|
| 1128 |
+
"rewards/rejected": -0.6872820258140564,
|
| 1129 |
+
"step": 1856
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 8.931992903607332,
|
| 1133 |
+
"grad_norm": 7.286854267120361,
|
| 1134 |
+
"learning_rate": 2.3961412515904335e-07,
|
| 1135 |
+
"log_odds_chosen": 4.6014862060546875,
|
| 1136 |
+
"log_odds_ratio": -0.23827242851257324,
|
| 1137 |
+
"logits/chosen": 0.8562659621238708,
|
| 1138 |
+
"logits/rejected": 0.5500348806381226,
|
| 1139 |
+
"logps/chosen": -0.8830623030662537,
|
| 1140 |
+
"logps/rejected": -4.95844841003418,
|
| 1141 |
+
"loss": 0.8922,
|
| 1142 |
+
"nll_loss": 0.8241187930107117,
|
| 1143 |
+
"rewards/accuracies": 0.91796875,
|
| 1144 |
+
"rewards/chosen": -0.132459357380867,
|
| 1145 |
+
"rewards/margins": 0.6113079190254211,
|
| 1146 |
+
"rewards/rejected": -0.743767261505127,
|
| 1147 |
+
"step": 1888
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 9.083382613837966,
|
| 1151 |
+
"grad_norm": 5.4477949142456055,
|
| 1152 |
+
"learning_rate": 2.3131747660339394e-07,
|
| 1153 |
+
"log_odds_chosen": 4.262630939483643,
|
| 1154 |
+
"log_odds_ratio": -0.25891953706741333,
|
| 1155 |
+
"logits/chosen": 0.7675349712371826,
|
| 1156 |
+
"logits/rejected": 0.51315838098526,
|
| 1157 |
+
"logps/chosen": -0.9374942779541016,
|
| 1158 |
+
"logps/rejected": -4.686108589172363,
|
| 1159 |
+
"loss": 0.8815,
|
| 1160 |
+
"nll_loss": 0.8197700381278992,
|
| 1161 |
+
"rewards/accuracies": 0.91015625,
|
| 1162 |
+
"rewards/chosen": -0.14062415063381195,
|
| 1163 |
+
"rewards/margins": 0.562292218208313,
|
| 1164 |
+
"rewards/rejected": -0.7029163837432861,
|
| 1165 |
+
"step": 1920
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 9.234772324068599,
|
| 1169 |
+
"grad_norm": 5.214437484741211,
|
| 1170 |
+
"learning_rate": 2.2304147384531036e-07,
|
| 1171 |
+
"log_odds_chosen": 4.728519439697266,
|
| 1172 |
+
"log_odds_ratio": -0.26717641949653625,
|
| 1173 |
+
"logits/chosen": 0.8268774747848511,
|
| 1174 |
+
"logits/rejected": 0.5454421639442444,
|
| 1175 |
+
"logps/chosen": -0.9330585598945618,
|
| 1176 |
+
"logps/rejected": -5.14246129989624,
|
| 1177 |
+
"loss": 0.8819,
|
| 1178 |
+
"nll_loss": 0.8327500820159912,
|
| 1179 |
+
"rewards/accuracies": 0.86328125,
|
| 1180 |
+
"rewards/chosen": -0.13995879888534546,
|
| 1181 |
+
"rewards/margins": 0.6314104795455933,
|
| 1182 |
+
"rewards/rejected": -0.771369218826294,
|
| 1183 |
+
"step": 1952
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 9.38616203429923,
|
| 1187 |
+
"grad_norm": 6.283268928527832,
|
| 1188 |
+
"learning_rate": 2.1479526258069083e-07,
|
| 1189 |
+
"log_odds_chosen": 4.715708255767822,
|
| 1190 |
+
"log_odds_ratio": -0.24205940961837769,
|
| 1191 |
+
"logits/chosen": 0.920197069644928,
|
| 1192 |
+
"logits/rejected": 0.5509434342384338,
|
| 1193 |
+
"logps/chosen": -0.9300947189331055,
|
| 1194 |
+
"logps/rejected": -5.131900787353516,
|
| 1195 |
+
"loss": 0.8768,
|
| 1196 |
+
"nll_loss": 0.8383646011352539,
|
| 1197 |
+
"rewards/accuracies": 0.87890625,
|
| 1198 |
+
"rewards/chosen": -0.13951420783996582,
|
| 1199 |
+
"rewards/margins": 0.6302710175514221,
|
| 1200 |
+
"rewards/rejected": -0.7697851657867432,
|
| 1201 |
+
"step": 1984
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 9.461856889414548,
|
| 1205 |
+
"eval_log_odds_chosen": 1.7867234945297241,
|
| 1206 |
+
"eval_log_odds_ratio": -0.18122754991054535,
|
| 1207 |
+
"eval_logits/chosen": 0.5212496519088745,
|
| 1208 |
+
"eval_logits/rejected": 0.4629932940006256,
|
| 1209 |
+
"eval_logps/chosen": -0.6597533226013184,
|
| 1210 |
+
"eval_logps/rejected": -1.7732388973236084,
|
| 1211 |
+
"eval_loss": 0.7272647619247437,
|
| 1212 |
+
"eval_nll_loss": 0.6736801266670227,
|
| 1213 |
+
"eval_rewards/accuracies": 1.0,
|
| 1214 |
+
"eval_rewards/chosen": -0.09896300733089447,
|
| 1215 |
+
"eval_rewards/margins": 0.16702282428741455,
|
| 1216 |
+
"eval_rewards/rejected": -0.2659858167171478,
|
| 1217 |
+
"eval_runtime": 1.766,
|
| 1218 |
+
"eval_samples_per_second": 77.575,
|
| 1219 |
+
"eval_steps_per_second": 10.192,
|
| 1220 |
+
"step": 2000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 9.537551744529864,
|
| 1224 |
+
"grad_norm": 4.955827713012695,
|
| 1225 |
+
"learning_rate": 2.065879555832674e-07,
|
| 1226 |
+
"log_odds_chosen": 4.195652008056641,
|
| 1227 |
+
"log_odds_ratio": -0.25658515095710754,
|
| 1228 |
+
"logits/chosen": 0.8670744895935059,
|
| 1229 |
+
"logits/rejected": 0.6037735939025879,
|
| 1230 |
+
"logps/chosen": -0.9333707094192505,
|
| 1231 |
+
"logps/rejected": -4.614899158477783,
|
| 1232 |
+
"loss": 0.8862,
|
| 1233 |
+
"nll_loss": 0.8495485782623291,
|
| 1234 |
+
"rewards/accuracies": 0.87109375,
|
| 1235 |
+
"rewards/chosen": -0.14000560343265533,
|
| 1236 |
+
"rewards/margins": 0.5522292852401733,
|
| 1237 |
+
"rewards/rejected": -0.6922348737716675,
|
| 1238 |
+
"step": 2016
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 9.688941454760498,
|
| 1242 |
+
"grad_norm": 5.796345233917236,
|
| 1243 |
+
"learning_rate": 1.984286226342056e-07,
|
| 1244 |
+
"log_odds_chosen": 4.511747360229492,
|
| 1245 |
+
"log_odds_ratio": -0.27976271510124207,
|
| 1246 |
+
"logits/chosen": 0.8292367458343506,
|
| 1247 |
+
"logits/rejected": 0.5408206582069397,
|
| 1248 |
+
"logps/chosen": -0.9318006038665771,
|
| 1249 |
+
"logps/rejected": -4.940333843231201,
|
| 1250 |
+
"loss": 0.8937,
|
| 1251 |
+
"nll_loss": 0.824824869632721,
|
| 1252 |
+
"rewards/accuracies": 0.86328125,
|
| 1253 |
+
"rewards/chosen": -0.13977007567882538,
|
| 1254 |
+
"rewards/margins": 0.6012800931930542,
|
| 1255 |
+
"rewards/rejected": -0.7410501837730408,
|
| 1256 |
+
"step": 2048
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 9.84033116499113,
|
| 1260 |
+
"grad_norm": 5.052858352661133,
|
| 1261 |
+
"learning_rate": 1.9032628049921556e-07,
|
| 1262 |
+
"log_odds_chosen": 4.3274006843566895,
|
| 1263 |
+
"log_odds_ratio": -0.2658219337463379,
|
| 1264 |
+
"logits/chosen": 0.7942694425582886,
|
| 1265 |
+
"logits/rejected": 0.5170871615409851,
|
| 1266 |
+
"logps/chosen": -0.9714781045913696,
|
| 1267 |
+
"logps/rejected": -4.801671028137207,
|
| 1268 |
+
"loss": 0.896,
|
| 1269 |
+
"nll_loss": 0.8439369201660156,
|
| 1270 |
+
"rewards/accuracies": 0.8828125,
|
| 1271 |
+
"rewards/chosen": -0.14572171866893768,
|
| 1272 |
+
"rewards/margins": 0.5745289325714111,
|
| 1273 |
+
"rewards/rejected": -0.72025066614151,
|
| 1274 |
+
"step": 2080
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 9.991720875221763,
|
| 1278 |
+
"grad_norm": 5.781661510467529,
|
| 1279 |
+
"learning_rate": 1.8228988296424875e-07,
|
| 1280 |
+
"log_odds_chosen": 4.903880596160889,
|
| 1281 |
+
"log_odds_ratio": -0.24629831314086914,
|
| 1282 |
+
"logits/chosen": 0.888929009437561,
|
| 1283 |
+
"logits/rejected": 0.5151562690734863,
|
| 1284 |
+
"logps/chosen": -0.9433965682983398,
|
| 1285 |
+
"logps/rejected": -5.327086925506592,
|
| 1286 |
+
"loss": 0.8761,
|
| 1287 |
+
"nll_loss": 0.8339080214500427,
|
| 1288 |
+
"rewards/accuracies": 0.8828125,
|
| 1289 |
+
"rewards/chosen": -0.1415095031261444,
|
| 1290 |
+
"rewards/margins": 0.6575536131858826,
|
| 1291 |
+
"rewards/rejected": -0.7990630865097046,
|
| 1292 |
+
"step": 2112
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 10.143110585452394,
|
| 1296 |
+
"grad_norm": 8.988626480102539,
|
| 1297 |
+
"learning_rate": 1.7432831094079352e-07,
|
| 1298 |
+
"log_odds_chosen": 4.3950042724609375,
|
| 1299 |
+
"log_odds_ratio": -0.28862205147743225,
|
| 1300 |
+
"logits/chosen": 0.8134148120880127,
|
| 1301 |
+
"logits/rejected": 0.5847084522247314,
|
| 1302 |
+
"logps/chosen": -1.0293586254119873,
|
| 1303 |
+
"logps/rejected": -4.959186553955078,
|
| 1304 |
+
"loss": 0.8813,
|
| 1305 |
+
"nll_loss": 0.8774588108062744,
|
| 1306 |
+
"rewards/accuracies": 0.85546875,
|
| 1307 |
+
"rewards/chosen": -0.15440379083156586,
|
| 1308 |
+
"rewards/margins": 0.5894742608070374,
|
| 1309 |
+
"rewards/rejected": -0.7438780069351196,
|
| 1310 |
+
"step": 2144
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 10.294500295683028,
|
| 1314 |
+
"grad_norm": 5.275697231292725,
|
| 1315 |
+
"learning_rate": 1.6645036265170313e-07,
|
| 1316 |
+
"log_odds_chosen": 5.46366548538208,
|
| 1317 |
+
"log_odds_ratio": -0.27606436610221863,
|
| 1318 |
+
"logits/chosen": 0.8438766598701477,
|
| 1319 |
+
"logits/rejected": 0.5199805498123169,
|
| 1320 |
+
"logps/chosen": -0.9803435802459717,
|
| 1321 |
+
"logps/rejected": -5.95693826675415,
|
| 1322 |
+
"loss": 0.8932,
|
| 1323 |
+
"nll_loss": 0.8328185677528381,
|
| 1324 |
+
"rewards/accuracies": 0.86328125,
|
| 1325 |
+
"rewards/chosen": -0.14705155789852142,
|
| 1326 |
+
"rewards/margins": 0.7464891076087952,
|
| 1327 |
+
"rewards/rejected": -0.8935407400131226,
|
| 1328 |
+
"step": 2176
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 10.445890005913661,
|
| 1332 |
+
"grad_norm": 6.923160552978516,
|
| 1333 |
+
"learning_rate": 1.5866474390840124e-07,
|
| 1334 |
+
"log_odds_chosen": 4.528408050537109,
|
| 1335 |
+
"log_odds_ratio": -0.25843387842178345,
|
| 1336 |
+
"logits/chosen": 0.8353314399719238,
|
| 1337 |
+
"logits/rejected": 0.5368306636810303,
|
| 1338 |
+
"logps/chosen": -0.9630373120307922,
|
| 1339 |
+
"logps/rejected": -4.988365173339844,
|
| 1340 |
+
"loss": 0.887,
|
| 1341 |
+
"nll_loss": 0.855586051940918,
|
| 1342 |
+
"rewards/accuracies": 0.8984375,
|
| 1343 |
+
"rewards/chosen": -0.14445561170578003,
|
| 1344 |
+
"rewards/margins": 0.6037992238998413,
|
| 1345 |
+
"rewards/rejected": -0.7482547760009766,
|
| 1346 |
+
"step": 2208
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 10.597279716144293,
|
| 1350 |
+
"grad_norm": 4.630692005157471,
|
| 1351 |
+
"learning_rate": 1.5098005849021078e-07,
|
| 1352 |
+
"log_odds_chosen": 4.724957466125488,
|
| 1353 |
+
"log_odds_ratio": -0.2811046242713928,
|
| 1354 |
+
"logits/chosen": 0.858523428440094,
|
| 1355 |
+
"logits/rejected": 0.5616721510887146,
|
| 1356 |
+
"logps/chosen": -0.9630488753318787,
|
| 1357 |
+
"logps/rejected": -5.188055038452148,
|
| 1358 |
+
"loss": 0.8694,
|
| 1359 |
+
"nll_loss": 0.858130693435669,
|
| 1360 |
+
"rewards/accuracies": 0.86328125,
|
| 1361 |
+
"rewards/chosen": -0.14445732533931732,
|
| 1362 |
+
"rewards/margins": 0.6337509155273438,
|
| 1363 |
+
"rewards/rejected": -0.778208315372467,
|
| 1364 |
+
"step": 2240
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 10.748669426374926,
|
| 1368 |
+
"grad_norm": 6.591275215148926,
|
| 1369 |
+
"learning_rate": 1.4340479863643656e-07,
|
| 1370 |
+
"log_odds_chosen": 4.770135402679443,
|
| 1371 |
+
"log_odds_ratio": -0.2736424207687378,
|
| 1372 |
+
"logits/chosen": 0.7936345934867859,
|
| 1373 |
+
"logits/rejected": 0.5366979837417603,
|
| 1374 |
+
"logps/chosen": -0.9466649889945984,
|
| 1375 |
+
"logps/rejected": -5.203468322753906,
|
| 1376 |
+
"loss": 0.8882,
|
| 1377 |
+
"nll_loss": 0.8353475332260132,
|
| 1378 |
+
"rewards/accuracies": 0.85546875,
|
| 1379 |
+
"rewards/chosen": -0.141999751329422,
|
| 1380 |
+
"rewards/margins": 0.6385205984115601,
|
| 1381 |
+
"rewards/rejected": -0.7805203795433044,
|
| 1382 |
+
"step": 2272
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 10.90005913660556,
|
| 1386 |
+
"grad_norm": 5.084187984466553,
|
| 1387 |
+
"learning_rate": 1.3594733566170925e-07,
|
| 1388 |
+
"log_odds_chosen": 4.994205474853516,
|
| 1389 |
+
"log_odds_ratio": -0.30068373680114746,
|
| 1390 |
+
"logits/chosen": 0.8074924945831299,
|
| 1391 |
+
"logits/rejected": 0.522384524345398,
|
| 1392 |
+
"logps/chosen": -0.9593102335929871,
|
| 1393 |
+
"logps/rejected": -5.447037220001221,
|
| 1394 |
+
"loss": 0.8834,
|
| 1395 |
+
"nll_loss": 0.8404646515846252,
|
| 1396 |
+
"rewards/accuracies": 0.8203125,
|
| 1397 |
+
"rewards/chosen": -0.14389653503894806,
|
| 1398 |
+
"rewards/margins": 0.673159122467041,
|
| 1399 |
+
"rewards/rejected": -0.8170557022094727,
|
| 1400 |
+
"step": 2304
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 11.051448846836191,
|
| 1404 |
+
"grad_norm": 5.465320110321045,
|
| 1405 |
+
"learning_rate": 1.2861591070496192e-07,
|
| 1406 |
+
"log_odds_chosen": 4.723004341125488,
|
| 1407 |
+
"log_odds_ratio": -0.25821179151535034,
|
| 1408 |
+
"logits/chosen": 0.8570014238357544,
|
| 1409 |
+
"logits/rejected": 0.5345165133476257,
|
| 1410 |
+
"logps/chosen": -0.9341294765472412,
|
| 1411 |
+
"logps/rejected": -5.139418601989746,
|
| 1412 |
+
"loss": 0.8586,
|
| 1413 |
+
"nll_loss": 0.8409022092819214,
|
| 1414 |
+
"rewards/accuracies": 0.89453125,
|
| 1415 |
+
"rewards/chosen": -0.14011943340301514,
|
| 1416 |
+
"rewards/margins": 0.6307933330535889,
|
| 1417 |
+
"rewards/rejected": -0.770912766456604,
|
| 1418 |
+
"step": 2336
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 11.202838557066825,
|
| 1422 |
+
"grad_norm": 5.109860420227051,
|
| 1423 |
+
"learning_rate": 1.2141862562226164e-07,
|
| 1424 |
+
"log_odds_chosen": 4.454768180847168,
|
| 1425 |
+
"log_odds_ratio": -0.24100762605667114,
|
| 1426 |
+
"logits/chosen": 0.7960795760154724,
|
| 1427 |
+
"logits/rejected": 0.511499285697937,
|
| 1428 |
+
"logps/chosen": -0.9228134751319885,
|
| 1429 |
+
"logps/rejected": -4.836323261260986,
|
| 1430 |
+
"loss": 0.8823,
|
| 1431 |
+
"nll_loss": 0.8171857595443726,
|
| 1432 |
+
"rewards/accuracies": 0.8984375,
|
| 1433 |
+
"rewards/chosen": -0.13842202723026276,
|
| 1434 |
+
"rewards/margins": 0.5870264172554016,
|
| 1435 |
+
"rewards/rejected": -0.725448489189148,
|
| 1436 |
+
"step": 2368
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 11.354228267297458,
|
| 1440 |
+
"grad_norm": 4.377430438995361,
|
| 1441 |
+
"learning_rate": 1.1436343403356016e-07,
|
| 1442 |
+
"log_odds_chosen": 4.902271270751953,
|
| 1443 |
+
"log_odds_ratio": -0.24684929847717285,
|
| 1444 |
+
"logits/chosen": 0.8083094358444214,
|
| 1445 |
+
"logits/rejected": 0.5171899199485779,
|
| 1446 |
+
"logps/chosen": -0.9131155610084534,
|
| 1447 |
+
"logps/rejected": -5.286437034606934,
|
| 1448 |
+
"loss": 0.8823,
|
| 1449 |
+
"nll_loss": 0.8163360953330994,
|
| 1450 |
+
"rewards/accuracies": 0.89453125,
|
| 1451 |
+
"rewards/chosen": -0.13696734607219696,
|
| 1452 |
+
"rewards/margins": 0.6559982299804688,
|
| 1453 |
+
"rewards/rejected": -0.7929655313491821,
|
| 1454 |
+
"step": 2400
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 11.354228267297458,
|
| 1458 |
+
"eval_log_odds_chosen": 1.8271435499191284,
|
| 1459 |
+
"eval_log_odds_ratio": -0.17579954862594604,
|
| 1460 |
+
"eval_logits/chosen": 0.49480167031288147,
|
| 1461 |
+
"eval_logits/rejected": 0.437588095664978,
|
| 1462 |
+
"eval_logps/chosen": -0.657990038394928,
|
| 1463 |
+
"eval_logps/rejected": -1.80092453956604,
|
| 1464 |
+
"eval_loss": 0.7247140407562256,
|
| 1465 |
+
"eval_nll_loss": 0.6719491481781006,
|
| 1466 |
+
"eval_rewards/accuracies": 1.0,
|
| 1467 |
+
"eval_rewards/chosen": -0.09869851171970367,
|
| 1468 |
+
"eval_rewards/margins": 0.1714402139186859,
|
| 1469 |
+
"eval_rewards/rejected": -0.2701387107372284,
|
| 1470 |
+
"eval_runtime": 1.7829,
|
| 1471 |
+
"eval_samples_per_second": 76.839,
|
| 1472 |
+
"eval_steps_per_second": 10.096,
|
| 1473 |
+
"step": 2400
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 11.50561797752809,
|
| 1477 |
+
"grad_norm": 6.997631072998047,
|
| 1478 |
+
"learning_rate": 1.0745813253325956e-07,
|
| 1479 |
+
"log_odds_chosen": 4.850367069244385,
|
| 1480 |
+
"log_odds_ratio": -0.23768070340156555,
|
| 1481 |
+
"logits/chosen": 0.8919247984886169,
|
| 1482 |
+
"logits/rejected": 0.5253655910491943,
|
| 1483 |
+
"logps/chosen": -0.9427354335784912,
|
| 1484 |
+
"logps/rejected": -5.268039226531982,
|
| 1485 |
+
"loss": 0.8907,
|
| 1486 |
+
"nll_loss": 0.8325998783111572,
|
| 1487 |
+
"rewards/accuracies": 0.90625,
|
| 1488 |
+
"rewards/chosen": -0.14141032099723816,
|
| 1489 |
+
"rewards/margins": 0.6487956643104553,
|
| 1490 |
+
"rewards/rejected": -0.7902059555053711,
|
| 1491 |
+
"step": 2432
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 11.657007687758723,
|
| 1495 |
+
"grad_norm": 6.977694988250732,
|
| 1496 |
+
"learning_rate": 1.007103520743035e-07,
|
| 1497 |
+
"log_odds_chosen": 4.430591106414795,
|
| 1498 |
+
"log_odds_ratio": -0.2736847698688507,
|
| 1499 |
+
"logits/chosen": 0.772072434425354,
|
| 1500 |
+
"logits/rejected": 0.5454930067062378,
|
| 1501 |
+
"logps/chosen": -0.972098171710968,
|
| 1502 |
+
"logps/rejected": -4.8969268798828125,
|
| 1503 |
+
"loss": 0.8668,
|
| 1504 |
+
"nll_loss": 0.864302396774292,
|
| 1505 |
+
"rewards/accuracies": 0.8828125,
|
| 1506 |
+
"rewards/chosen": -0.14581473171710968,
|
| 1507 |
+
"rewards/margins": 0.5887242555618286,
|
| 1508 |
+
"rewards/rejected": -0.7345390319824219,
|
| 1509 |
+
"step": 2464
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 11.808397397989355,
|
| 1513 |
+
"grad_norm": 9.901198387145996,
|
| 1514 |
+
"learning_rate": 9.412754953531663e-08,
|
| 1515 |
+
"log_odds_chosen": 5.721859455108643,
|
| 1516 |
+
"log_odds_ratio": -0.2376585453748703,
|
| 1517 |
+
"logits/chosen": 0.9159454107284546,
|
| 1518 |
+
"logits/rejected": 0.49302536249160767,
|
| 1519 |
+
"logps/chosen": -0.905667781829834,
|
| 1520 |
+
"logps/rejected": -6.09743070602417,
|
| 1521 |
+
"loss": 0.8778,
|
| 1522 |
+
"nll_loss": 0.8210791945457458,
|
| 1523 |
+
"rewards/accuracies": 0.8984375,
|
| 1524 |
+
"rewards/chosen": -0.135850191116333,
|
| 1525 |
+
"rewards/margins": 0.7787644267082214,
|
| 1526 |
+
"rewards/rejected": -0.9146146178245544,
|
| 1527 |
+
"step": 2496
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 11.959787108219988,
|
| 1531 |
+
"grad_norm": 6.6628241539001465,
|
| 1532 |
+
"learning_rate": 8.771699948011203e-08,
|
| 1533 |
+
"log_odds_chosen": 4.282519817352295,
|
| 1534 |
+
"log_odds_ratio": -0.2792586088180542,
|
| 1535 |
+
"logits/chosen": 0.790172815322876,
|
| 1536 |
+
"logits/rejected": 0.563973069190979,
|
| 1537 |
+
"logps/chosen": -0.9786302447319031,
|
| 1538 |
+
"logps/rejected": -4.77611780166626,
|
| 1539 |
+
"loss": 0.8802,
|
| 1540 |
+
"nll_loss": 0.8442527651786804,
|
| 1541 |
+
"rewards/accuracies": 0.84765625,
|
| 1542 |
+
"rewards/chosen": -0.14679455757141113,
|
| 1543 |
+
"rewards/margins": 0.5696231722831726,
|
| 1544 |
+
"rewards/rejected": -0.716417670249939,
|
| 1545 |
+
"step": 2528
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 12.111176818450621,
|
| 1549 |
+
"grad_norm": 5.591745853424072,
|
| 1550 |
+
"learning_rate": 8.148578611867113e-08,
|
| 1551 |
+
"log_odds_chosen": 4.849425315856934,
|
| 1552 |
+
"log_odds_ratio": -0.29553845524787903,
|
| 1553 |
+
"logits/chosen": 0.8502916097640991,
|
| 1554 |
+
"logits/rejected": 0.5881719589233398,
|
| 1555 |
+
"logps/chosen": -0.9942740201950073,
|
| 1556 |
+
"logps/rejected": -5.380496025085449,
|
| 1557 |
+
"loss": 0.8794,
|
| 1558 |
+
"nll_loss": 0.894903302192688,
|
| 1559 |
+
"rewards/accuracies": 0.83984375,
|
| 1560 |
+
"rewards/chosen": -0.1491411030292511,
|
| 1561 |
+
"rewards/margins": 0.6579334139823914,
|
| 1562 |
+
"rewards/rejected": -0.8070744276046753,
|
| 1563 |
+
"step": 2560
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 12.262566528681253,
|
| 1567 |
+
"grad_norm": 4.799871921539307,
|
| 1568 |
+
"learning_rate": 7.544079547848181e-08,
|
| 1569 |
+
"log_odds_chosen": 4.629427909851074,
|
| 1570 |
+
"log_odds_ratio": -0.2579698860645294,
|
| 1571 |
+
"logits/chosen": 0.8144665360450745,
|
| 1572 |
+
"logits/rejected": 0.5345531702041626,
|
| 1573 |
+
"logps/chosen": -0.9962482452392578,
|
| 1574 |
+
"logps/rejected": -5.126289367675781,
|
| 1575 |
+
"loss": 0.8853,
|
| 1576 |
+
"nll_loss": 0.8719948530197144,
|
| 1577 |
+
"rewards/accuracies": 0.87890625,
|
| 1578 |
+
"rewards/chosen": -0.14943724870681763,
|
| 1579 |
+
"rewards/margins": 0.6195061802864075,
|
| 1580 |
+
"rewards/rejected": -0.7689434885978699,
|
| 1581 |
+
"step": 2592
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 12.413956238911886,
|
| 1585 |
+
"grad_norm": 5.2031779289245605,
|
| 1586 |
+
"learning_rate": 6.958870779488446e-08,
|
| 1587 |
+
"log_odds_chosen": 5.763055801391602,
|
| 1588 |
+
"log_odds_ratio": -0.24303670227527618,
|
| 1589 |
+
"logits/chosen": 0.85135418176651,
|
| 1590 |
+
"logits/rejected": 0.5018079876899719,
|
| 1591 |
+
"logps/chosen": -0.9315154552459717,
|
| 1592 |
+
"logps/rejected": -6.163926124572754,
|
| 1593 |
+
"loss": 0.8732,
|
| 1594 |
+
"nll_loss": 0.8289435505867004,
|
| 1595 |
+
"rewards/accuracies": 0.875,
|
| 1596 |
+
"rewards/chosen": -0.13972733914852142,
|
| 1597 |
+
"rewards/margins": 0.78486168384552,
|
| 1598 |
+
"rewards/rejected": -0.9245890378952026,
|
| 1599 |
+
"step": 2624
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 12.56534594914252,
|
| 1603 |
+
"grad_norm": 4.5774712562561035,
|
| 1604 |
+
"learning_rate": 6.393599012883707e-08,
|
| 1605 |
+
"log_odds_chosen": 4.685327529907227,
|
| 1606 |
+
"log_odds_ratio": -0.2833007574081421,
|
| 1607 |
+
"logits/chosen": 0.7489104270935059,
|
| 1608 |
+
"logits/rejected": 0.5779923796653748,
|
| 1609 |
+
"logps/chosen": -0.9675414562225342,
|
| 1610 |
+
"logps/rejected": -5.168377876281738,
|
| 1611 |
+
"loss": 0.8694,
|
| 1612 |
+
"nll_loss": 0.8434449434280396,
|
| 1613 |
+
"rewards/accuracies": 0.875,
|
| 1614 |
+
"rewards/chosen": -0.14513123035430908,
|
| 1615 |
+
"rewards/margins": 0.6301255226135254,
|
| 1616 |
+
"rewards/rejected": -0.7752567529678345,
|
| 1617 |
+
"step": 2656
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 12.716735659373152,
|
| 1621 |
+
"grad_norm": 5.854611396789551,
|
| 1622 |
+
"learning_rate": 5.848888922025552e-08,
|
| 1623 |
+
"log_odds_chosen": 5.014122009277344,
|
| 1624 |
+
"log_odds_ratio": -0.23267918825149536,
|
| 1625 |
+
"logits/chosen": 0.8252905607223511,
|
| 1626 |
+
"logits/rejected": 0.4858684539794922,
|
| 1627 |
+
"logps/chosen": -0.8893996477127075,
|
| 1628 |
+
"logps/rejected": -5.326512336730957,
|
| 1629 |
+
"loss": 0.878,
|
| 1630 |
+
"nll_loss": 0.8163630366325378,
|
| 1631 |
+
"rewards/accuracies": 0.8828125,
|
| 1632 |
+
"rewards/chosen": -0.13340994715690613,
|
| 1633 |
+
"rewards/margins": 0.6655669212341309,
|
| 1634 |
+
"rewards/rejected": -0.7989768981933594,
|
| 1635 |
+
"step": 2688
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 12.868125369603785,
|
| 1639 |
+
"grad_norm": 5.542015075683594,
|
| 1640 |
+
"learning_rate": 5.325342458482779e-08,
|
| 1641 |
+
"log_odds_chosen": 5.052638530731201,
|
| 1642 |
+
"log_odds_ratio": -0.2500526010990143,
|
| 1643 |
+
"logits/chosen": 0.8215246796607971,
|
| 1644 |
+
"logits/rejected": 0.573950469493866,
|
| 1645 |
+
"logps/chosen": -0.8597905039787292,
|
| 1646 |
+
"logps/rejected": -5.335259437561035,
|
| 1647 |
+
"loss": 0.8812,
|
| 1648 |
+
"nll_loss": 0.8173032999038696,
|
| 1649 |
+
"rewards/accuracies": 0.875,
|
| 1650 |
+
"rewards/chosen": -0.12896858155727386,
|
| 1651 |
+
"rewards/margins": 0.6713204383850098,
|
| 1652 |
+
"rewards/rejected": -0.8002889156341553,
|
| 1653 |
+
"step": 2720
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 13.019515079834418,
|
| 1657 |
+
"grad_norm": 7.424806118011475,
|
| 1658 |
+
"learning_rate": 4.823538186193096e-08,
|
| 1659 |
+
"log_odds_chosen": 5.35725212097168,
|
| 1660 |
+
"log_odds_ratio": -0.23181939125061035,
|
| 1661 |
+
"logits/chosen": 0.8148990273475647,
|
| 1662 |
+
"logits/rejected": 0.4551333785057068,
|
| 1663 |
+
"logps/chosen": -0.9124429225921631,
|
| 1664 |
+
"logps/rejected": -5.717087268829346,
|
| 1665 |
+
"loss": 0.8778,
|
| 1666 |
+
"nll_loss": 0.8277573585510254,
|
| 1667 |
+
"rewards/accuracies": 0.91015625,
|
| 1668 |
+
"rewards/chosen": -0.13686645030975342,
|
| 1669 |
+
"rewards/margins": 0.7206966876983643,
|
| 1670 |
+
"rewards/rejected": -0.8575630784034729,
|
| 1671 |
+
"step": 2752
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 13.17090479006505,
|
| 1675 |
+
"grad_norm": 6.039958953857422,
|
| 1676 |
+
"learning_rate": 4.3440306421001324e-08,
|
| 1677 |
+
"log_odds_chosen": 5.5131001472473145,
|
| 1678 |
+
"log_odds_ratio": -0.24206629395484924,
|
| 1679 |
+
"logits/chosen": 0.873075008392334,
|
| 1680 |
+
"logits/rejected": 0.5212752223014832,
|
| 1681 |
+
"logps/chosen": -0.8922577500343323,
|
| 1682 |
+
"logps/rejected": -5.86539888381958,
|
| 1683 |
+
"loss": 0.8901,
|
| 1684 |
+
"nll_loss": 0.8136817216873169,
|
| 1685 |
+
"rewards/accuracies": 0.88671875,
|
| 1686 |
+
"rewards/chosen": -0.13383866846561432,
|
| 1687 |
+
"rewards/margins": 0.745971143245697,
|
| 1688 |
+
"rewards/rejected": -0.8798097968101501,
|
| 1689 |
+
"step": 2784
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 13.246599645180366,
|
| 1693 |
+
"eval_log_odds_chosen": 1.8457978963851929,
|
| 1694 |
+
"eval_log_odds_ratio": -0.17291945219039917,
|
| 1695 |
+
"eval_logits/chosen": 0.5009181499481201,
|
| 1696 |
+
"eval_logits/rejected": 0.446205198764801,
|
| 1697 |
+
"eval_logps/chosen": -0.6597917675971985,
|
| 1698 |
+
"eval_logps/rejected": -1.8198742866516113,
|
| 1699 |
+
"eval_loss": 0.7256795763969421,
|
| 1700 |
+
"eval_nll_loss": 0.6736116409301758,
|
| 1701 |
+
"eval_rewards/accuracies": 1.0,
|
| 1702 |
+
"eval_rewards/chosen": -0.09896877408027649,
|
| 1703 |
+
"eval_rewards/margins": 0.17401237785816193,
|
| 1704 |
+
"eval_rewards/rejected": -0.2729811668395996,
|
| 1705 |
+
"eval_runtime": 1.7675,
|
| 1706 |
+
"eval_samples_per_second": 77.512,
|
| 1707 |
+
"eval_steps_per_second": 10.184,
|
| 1708 |
+
"step": 2800
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 13.322294500295683,
|
| 1712 |
+
"grad_norm": 4.649291515350342,
|
| 1713 |
+
"learning_rate": 3.887349723342303e-08,
|
| 1714 |
+
"log_odds_chosen": 5.655206203460693,
|
| 1715 |
+
"log_odds_ratio": -0.22572118043899536,
|
| 1716 |
+
"logits/chosen": 0.8335084915161133,
|
| 1717 |
+
"logits/rejected": 0.4884824752807617,
|
| 1718 |
+
"logps/chosen": -0.8668183088302612,
|
| 1719 |
+
"logps/rejected": -5.9456024169921875,
|
| 1720 |
+
"loss": 0.8773,
|
| 1721 |
+
"nll_loss": 0.7930561900138855,
|
| 1722 |
+
"rewards/accuracies": 0.90234375,
|
| 1723 |
+
"rewards/chosen": -0.13002273440361023,
|
| 1724 |
+
"rewards/margins": 0.7618176937103271,
|
| 1725 |
+
"rewards/rejected": -0.8918405175209045,
|
| 1726 |
+
"step": 2816
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 13.473684210526315,
|
| 1730 |
+
"grad_norm": 5.706801414489746,
|
| 1731 |
+
"learning_rate": 3.454000101670901e-08,
|
| 1732 |
+
"log_odds_chosen": 4.356830596923828,
|
| 1733 |
+
"log_odds_ratio": -0.24235375225543976,
|
| 1734 |
+
"logits/chosen": 0.7453078031539917,
|
| 1735 |
+
"logits/rejected": 0.5251801609992981,
|
| 1736 |
+
"logps/chosen": -0.9370274543762207,
|
| 1737 |
+
"logps/rejected": -4.772754192352295,
|
| 1738 |
+
"loss": 0.8771,
|
| 1739 |
+
"nll_loss": 0.8157171010971069,
|
| 1740 |
+
"rewards/accuracies": 0.88671875,
|
| 1741 |
+
"rewards/chosen": -0.14055413007736206,
|
| 1742 |
+
"rewards/margins": 0.5753591060638428,
|
| 1743 |
+
"rewards/rejected": -0.7159131765365601,
|
| 1744 |
+
"step": 2848
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 13.625073920756948,
|
| 1748 |
+
"grad_norm": 6.6824140548706055,
|
| 1749 |
+
"learning_rate": 3.044460665744283e-08,
|
| 1750 |
+
"log_odds_chosen": 4.974400043487549,
|
| 1751 |
+
"log_odds_ratio": -0.24002020061016083,
|
| 1752 |
+
"logits/chosen": 0.7889403700828552,
|
| 1753 |
+
"logits/rejected": 0.4931294322013855,
|
| 1754 |
+
"logps/chosen": -0.9762779474258423,
|
| 1755 |
+
"logps/rejected": -5.440495491027832,
|
| 1756 |
+
"loss": 0.8849,
|
| 1757 |
+
"nll_loss": 0.8199655413627625,
|
| 1758 |
+
"rewards/accuracies": 0.8984375,
|
| 1759 |
+
"rewards/chosen": -0.14644168317317963,
|
| 1760 |
+
"rewards/margins": 0.6696327328681946,
|
| 1761 |
+
"rewards/rejected": -0.8160744905471802,
|
| 1762 |
+
"step": 2880
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 13.776463630987582,
|
| 1766 |
+
"grad_norm": 9.858070373535156,
|
| 1767 |
+
"learning_rate": 2.659183991914696e-08,
|
| 1768 |
+
"log_odds_chosen": 4.271711349487305,
|
| 1769 |
+
"log_odds_ratio": -0.25790902972221375,
|
| 1770 |
+
"logits/chosen": 0.7586400508880615,
|
| 1771 |
+
"logits/rejected": 0.5483137369155884,
|
| 1772 |
+
"logps/chosen": -0.9079785346984863,
|
| 1773 |
+
"logps/rejected": -4.65129280090332,
|
| 1774 |
+
"loss": 0.8755,
|
| 1775 |
+
"nll_loss": 0.8172128200531006,
|
| 1776 |
+
"rewards/accuracies": 0.87890625,
|
| 1777 |
+
"rewards/chosen": -0.1361967921257019,
|
| 1778 |
+
"rewards/margins": 0.561497151851654,
|
| 1779 |
+
"rewards/rejected": -0.697693943977356,
|
| 1780 |
+
"step": 2912
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 13.927853341218214,
|
| 1784 |
+
"grad_norm": 4.99421501159668,
|
| 1785 |
+
"learning_rate": 2.298595844092377e-08,
|
| 1786 |
+
"log_odds_chosen": 5.054343223571777,
|
| 1787 |
+
"log_odds_ratio": -0.2358601987361908,
|
| 1788 |
+
"logits/chosen": 0.7982761859893799,
|
| 1789 |
+
"logits/rejected": 0.5060718655586243,
|
| 1790 |
+
"logps/chosen": -0.9570282697677612,
|
| 1791 |
+
"logps/rejected": -5.482752799987793,
|
| 1792 |
+
"loss": 0.8707,
|
| 1793 |
+
"nll_loss": 0.8115738034248352,
|
| 1794 |
+
"rewards/accuracies": 0.90234375,
|
| 1795 |
+
"rewards/chosen": -0.143554225564003,
|
| 1796 |
+
"rewards/margins": 0.6788586974143982,
|
| 1797 |
+
"rewards/rejected": -0.82241290807724,
|
| 1798 |
+
"step": 2944
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 14.079243051448847,
|
| 1802 |
+
"grad_norm": 17.175851821899414,
|
| 1803 |
+
"learning_rate": 1.9630947032398066e-08,
|
| 1804 |
+
"log_odds_chosen": 5.8499908447265625,
|
| 1805 |
+
"log_odds_ratio": -0.22148607671260834,
|
| 1806 |
+
"logits/chosen": 0.817506730556488,
|
| 1807 |
+
"logits/rejected": 0.44914665818214417,
|
| 1808 |
+
"logps/chosen": -0.8968250751495361,
|
| 1809 |
+
"logps/rejected": -6.185724258422852,
|
| 1810 |
+
"loss": 0.8673,
|
| 1811 |
+
"nll_loss": 0.8207356333732605,
|
| 1812 |
+
"rewards/accuracies": 0.921875,
|
| 1813 |
+
"rewards/chosen": -0.13452376425266266,
|
| 1814 |
+
"rewards/margins": 0.7933349013328552,
|
| 1815 |
+
"rewards/rejected": -0.9278587698936462,
|
| 1816 |
+
"step": 2976
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 14.23063276167948,
|
| 1820 |
+
"grad_norm": 7.170802593231201,
|
| 1821 |
+
"learning_rate": 1.653051327015911e-08,
|
| 1822 |
+
"log_odds_chosen": 4.76658296585083,
|
| 1823 |
+
"log_odds_ratio": -0.24812592566013336,
|
| 1824 |
+
"logits/chosen": 0.8145585060119629,
|
| 1825 |
+
"logits/rejected": 0.5187351703643799,
|
| 1826 |
+
"logps/chosen": -0.9258391261100769,
|
| 1827 |
+
"logps/rejected": -5.176287651062012,
|
| 1828 |
+
"loss": 0.8781,
|
| 1829 |
+
"nll_loss": 0.8292718529701233,
|
| 1830 |
+
"rewards/accuracies": 0.90625,
|
| 1831 |
+
"rewards/chosen": -0.13887587189674377,
|
| 1832 |
+
"rewards/margins": 0.6375671625137329,
|
| 1833 |
+
"rewards/rejected": -0.7764431834220886,
|
| 1834 |
+
"step": 3008
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 14.382022471910112,
|
| 1838 |
+
"grad_norm": 5.404478073120117,
|
| 1839 |
+
"learning_rate": 1.368808340056879e-08,
|
| 1840 |
+
"log_odds_chosen": 5.262024879455566,
|
| 1841 |
+
"log_odds_ratio": -0.22128547728061676,
|
| 1842 |
+
"logits/chosen": 0.7849254608154297,
|
| 1843 |
+
"logits/rejected": 0.4733457863330841,
|
| 1844 |
+
"logps/chosen": -0.9194588661193848,
|
| 1845 |
+
"logps/rejected": -5.613149166107178,
|
| 1846 |
+
"loss": 0.8665,
|
| 1847 |
+
"nll_loss": 0.8110780715942383,
|
| 1848 |
+
"rewards/accuracies": 0.8828125,
|
| 1849 |
+
"rewards/chosen": -0.1379188597202301,
|
| 1850 |
+
"rewards/margins": 0.704053521156311,
|
| 1851 |
+
"rewards/rejected": -0.8419723510742188,
|
| 1852 |
+
"step": 3040
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 14.533412182140745,
|
| 1856 |
+
"grad_norm": 4.717693328857422,
|
| 1857 |
+
"learning_rate": 1.1106798553464802e-08,
|
| 1858 |
+
"log_odds_chosen": 5.532874584197998,
|
| 1859 |
+
"log_odds_ratio": -0.23889514803886414,
|
| 1860 |
+
"logits/chosen": 0.887575626373291,
|
| 1861 |
+
"logits/rejected": 0.503061056137085,
|
| 1862 |
+
"logps/chosen": -0.9478439092636108,
|
| 1863 |
+
"logps/rejected": -5.9591827392578125,
|
| 1864 |
+
"loss": 0.8689,
|
| 1865 |
+
"nll_loss": 0.8499802947044373,
|
| 1866 |
+
"rewards/accuracies": 0.9140625,
|
| 1867 |
+
"rewards/chosen": -0.1421765685081482,
|
| 1868 |
+
"rewards/margins": 0.7517008185386658,
|
| 1869 |
+
"rewards/rejected": -0.893877387046814,
|
| 1870 |
+
"step": 3072
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 14.684801892371379,
|
| 1874 |
+
"grad_norm": 7.475513458251953,
|
| 1875 |
+
"learning_rate": 8.789511270941269e-09,
|
| 1876 |
+
"log_odds_chosen": 4.4497551918029785,
|
| 1877 |
+
"log_odds_ratio": -0.27013376355171204,
|
| 1878 |
+
"logits/chosen": 0.7935608625411987,
|
| 1879 |
+
"logits/rejected": 0.5559485554695129,
|
| 1880 |
+
"logps/chosen": -0.9605445861816406,
|
| 1881 |
+
"logps/rejected": -4.917541980743408,
|
| 1882 |
+
"loss": 0.8786,
|
| 1883 |
+
"nll_loss": 0.8641871213912964,
|
| 1884 |
+
"rewards/accuracies": 0.8828125,
|
| 1885 |
+
"rewards/chosen": -0.1440816968679428,
|
| 1886 |
+
"rewards/margins": 0.5935496091842651,
|
| 1887 |
+
"rewards/rejected": -0.7376313209533691,
|
| 1888 |
+
"step": 3104
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 14.83619160260201,
|
| 1892 |
+
"grad_norm": 6.8675408363342285,
|
| 1893 |
+
"learning_rate": 6.738782355044048e-09,
|
| 1894 |
+
"log_odds_chosen": 4.509281635284424,
|
| 1895 |
+
"log_odds_ratio": -0.27578622102737427,
|
| 1896 |
+
"logits/chosen": 0.7721443772315979,
|
| 1897 |
+
"logits/rejected": 0.5139036774635315,
|
| 1898 |
+
"logps/chosen": -0.9913955926895142,
|
| 1899 |
+
"logps/rejected": -5.035284042358398,
|
| 1900 |
+
"loss": 0.8838,
|
| 1901 |
+
"nll_loss": 0.8683611154556274,
|
| 1902 |
+
"rewards/accuracies": 0.88671875,
|
| 1903 |
+
"rewards/chosen": -0.14870934188365936,
|
| 1904 |
+
"rewards/margins": 0.6065833568572998,
|
| 1905 |
+
"rewards/rejected": -0.7552926540374756,
|
| 1906 |
+
"step": 3136
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 14.987581312832644,
|
| 1910 |
+
"grad_norm": 7.102670669555664,
|
| 1911 |
+
"learning_rate": 4.956878037864043e-09,
|
| 1912 |
+
"log_odds_chosen": 4.306816101074219,
|
| 1913 |
+
"log_odds_ratio": -0.30200034379959106,
|
| 1914 |
+
"logits/chosen": 0.8607514500617981,
|
| 1915 |
+
"logits/rejected": 0.591871440410614,
|
| 1916 |
+
"logps/chosen": -0.9792557954788208,
|
| 1917 |
+
"logps/rejected": -4.773169040679932,
|
| 1918 |
+
"loss": 0.8869,
|
| 1919 |
+
"nll_loss": 0.8911793231964111,
|
| 1920 |
+
"rewards/accuracies": 0.859375,
|
| 1921 |
+
"rewards/chosen": -0.1468883752822876,
|
| 1922 |
+
"rewards/margins": 0.569087028503418,
|
| 1923 |
+
"rewards/rejected": -0.7159753441810608,
|
| 1924 |
+
"step": 3168
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 15.138971023063275,
|
| 1928 |
+
"grad_norm": 4.992292881011963,
|
| 1929 |
+
"learning_rate": 3.4457674771554422e-09,
|
| 1930 |
+
"log_odds_chosen": 4.759942054748535,
|
| 1931 |
+
"log_odds_ratio": -0.2575688362121582,
|
| 1932 |
+
"logits/chosen": 0.7185624241828918,
|
| 1933 |
+
"logits/rejected": 0.42112159729003906,
|
| 1934 |
+
"logps/chosen": -0.9415456652641296,
|
| 1935 |
+
"logps/rejected": -5.170385360717773,
|
| 1936 |
+
"loss": 0.858,
|
| 1937 |
+
"nll_loss": 0.8277443647384644,
|
| 1938 |
+
"rewards/accuracies": 0.8828125,
|
| 1939 |
+
"rewards/chosen": -0.14123186469078064,
|
| 1940 |
+
"rewards/margins": 0.6343258619308472,
|
| 1941 |
+
"rewards/rejected": -0.775557816028595,
|
| 1942 |
+
"step": 3200
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 15.138971023063275,
|
| 1946 |
+
"eval_log_odds_chosen": 1.8564934730529785,
|
| 1947 |
+
"eval_log_odds_ratio": -0.17145967483520508,
|
| 1948 |
+
"eval_logits/chosen": 0.48080742359161377,
|
| 1949 |
+
"eval_logits/rejected": 0.4276208281517029,
|
| 1950 |
+
"eval_logps/chosen": -0.6593887209892273,
|
| 1951 |
+
"eval_logps/rejected": -1.8252443075180054,
|
| 1952 |
+
"eval_loss": 0.7243954539299011,
|
| 1953 |
+
"eval_nll_loss": 0.6726279854774475,
|
| 1954 |
+
"eval_rewards/accuracies": 1.0,
|
| 1955 |
+
"eval_rewards/chosen": -0.09890830516815186,
|
| 1956 |
+
"eval_rewards/margins": 0.17487837374210358,
|
| 1957 |
+
"eval_rewards/rejected": -0.27378666400909424,
|
| 1958 |
+
"eval_runtime": 1.7744,
|
| 1959 |
+
"eval_samples_per_second": 77.208,
|
| 1960 |
+
"eval_steps_per_second": 10.144,
|
| 1961 |
+
"step": 3200
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 15.290360733293909,
|
| 1965 |
+
"grad_norm": 6.751287937164307,
|
| 1966 |
+
"learning_rate": 2.2071205802468297e-09,
|
| 1967 |
+
"log_odds_chosen": 4.854089736938477,
|
| 1968 |
+
"log_odds_ratio": -0.2636704742908478,
|
| 1969 |
+
"logits/chosen": 0.7567326426506042,
|
| 1970 |
+
"logits/rejected": 0.527582585811615,
|
| 1971 |
+
"logps/chosen": -0.9423821568489075,
|
| 1972 |
+
"logps/rejected": -5.277737617492676,
|
| 1973 |
+
"loss": 0.8852,
|
| 1974 |
+
"nll_loss": 0.844541609287262,
|
| 1975 |
+
"rewards/accuracies": 0.875,
|
| 1976 |
+
"rewards/chosen": -0.14135733246803284,
|
| 1977 |
+
"rewards/margins": 0.6503032445907593,
|
| 1978 |
+
"rewards/rejected": -0.7916606068611145,
|
| 1979 |
+
"step": 3232
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 15.441750443524542,
|
| 1983 |
+
"grad_norm": 5.534750938415527,
|
| 1984 |
+
"learning_rate": 1.2423061586496476e-09,
|
| 1985 |
+
"log_odds_chosen": 5.184489727020264,
|
| 1986 |
+
"log_odds_ratio": -0.24983780086040497,
|
| 1987 |
+
"logits/chosen": 0.8209244608879089,
|
| 1988 |
+
"logits/rejected": 0.5052769780158997,
|
| 1989 |
+
"logps/chosen": -0.9556353688240051,
|
| 1990 |
+
"logps/rejected": -5.621804237365723,
|
| 1991 |
+
"loss": 0.8706,
|
| 1992 |
+
"nll_loss": 0.8418364524841309,
|
| 1993 |
+
"rewards/accuracies": 0.88671875,
|
| 1994 |
+
"rewards/chosen": -0.14334531128406525,
|
| 1995 |
+
"rewards/margins": 0.699925422668457,
|
| 1996 |
+
"rewards/rejected": -0.8432707786560059,
|
| 1997 |
+
"step": 3264
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 15.593140153755174,
|
| 2001 |
+
"grad_norm": 5.217104434967041,
|
| 2002 |
+
"learning_rate": 5.523904154037528e-10,
|
| 2003 |
+
"log_odds_chosen": 5.348480701446533,
|
| 2004 |
+
"log_odds_ratio": -0.2507275640964508,
|
| 2005 |
+
"logits/chosen": 0.8220376372337341,
|
| 2006 |
+
"logits/rejected": 0.5271560549736023,
|
| 2007 |
+
"logps/chosen": -0.9200209975242615,
|
| 2008 |
+
"logps/rejected": -5.755062103271484,
|
| 2009 |
+
"loss": 0.887,
|
| 2010 |
+
"nll_loss": 0.8451349139213562,
|
| 2011 |
+
"rewards/accuracies": 0.85546875,
|
| 2012 |
+
"rewards/chosen": -0.1380031555891037,
|
| 2013 |
+
"rewards/margins": 0.7252561450004578,
|
| 2014 |
+
"rewards/rejected": -0.8632593154907227,
|
| 2015 |
+
"step": 3296
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 15.744529863985807,
|
| 2019 |
+
"grad_norm": 6.9226460456848145,
|
| 2020 |
+
"learning_rate": 1.3813576683111006e-10,
|
| 2021 |
+
"log_odds_chosen": 4.370879650115967,
|
| 2022 |
+
"log_odds_ratio": -0.24154168367385864,
|
| 2023 |
+
"logits/chosen": 0.7712342739105225,
|
| 2024 |
+
"logits/rejected": 0.5409867763519287,
|
| 2025 |
+
"logps/chosen": -0.9708598256111145,
|
| 2026 |
+
"logps/rejected": -4.831565856933594,
|
| 2027 |
+
"loss": 0.8729,
|
| 2028 |
+
"nll_loss": 0.8363229036331177,
|
| 2029 |
+
"rewards/accuracies": 0.921875,
|
| 2030 |
+
"rewards/chosen": -0.14562898874282837,
|
| 2031 |
+
"rewards/margins": 0.5791059136390686,
|
| 2032 |
+
"rewards/rejected": -0.724734902381897,
|
| 2033 |
+
"step": 3328
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 15.89591957421644,
|
| 2037 |
+
"grad_norm": 7.291532516479492,
|
| 2038 |
+
"learning_rate": 0.0,
|
| 2039 |
+
"log_odds_chosen": 5.1468186378479,
|
| 2040 |
+
"log_odds_ratio": -0.2334214597940445,
|
| 2041 |
+
"logits/chosen": 0.8100905418395996,
|
| 2042 |
+
"logits/rejected": 0.48369458317756653,
|
| 2043 |
+
"logps/chosen": -0.8902687430381775,
|
| 2044 |
+
"logps/rejected": -5.482838153839111,
|
| 2045 |
+
"loss": 0.883,
|
| 2046 |
+
"nll_loss": 0.8243392705917358,
|
| 2047 |
+
"rewards/accuracies": 0.890625,
|
| 2048 |
+
"rewards/chosen": -0.1335403174161911,
|
| 2049 |
+
"rewards/margins": 0.688885509967804,
|
| 2050 |
+
"rewards/rejected": -0.8224257826805115,
|
| 2051 |
+
"step": 3360
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 15.89591957421644,
|
| 2055 |
+
"eval_log_odds_chosen": 1.8541311025619507,
|
| 2056 |
+
"eval_log_odds_ratio": -0.17156726121902466,
|
| 2057 |
+
"eval_logits/chosen": 0.4940509796142578,
|
| 2058 |
+
"eval_logits/rejected": 0.4394443929195404,
|
| 2059 |
+
"eval_logps/chosen": -0.6573522090911865,
|
| 2060 |
+
"eval_logps/rejected": -1.8197245597839355,
|
| 2061 |
+
"eval_loss": 0.7246665954589844,
|
| 2062 |
+
"eval_nll_loss": 0.6722227334976196,
|
| 2063 |
+
"eval_rewards/accuracies": 1.0,
|
| 2064 |
+
"eval_rewards/chosen": -0.09860283136367798,
|
| 2065 |
+
"eval_rewards/margins": 0.17435584962368011,
|
| 2066 |
+
"eval_rewards/rejected": -0.2729586660861969,
|
| 2067 |
+
"eval_runtime": 1.7715,
|
| 2068 |
+
"eval_samples_per_second": 77.334,
|
| 2069 |
+
"eval_steps_per_second": 10.161,
|
| 2070 |
+
"step": 3360
|
| 2071 |
+
}
|
| 2072 |
+
],
|
| 2073 |
+
"logging_steps": 32,
|
| 2074 |
+
"max_steps": 3360,
|
| 2075 |
+
"num_input_tokens_seen": 0,
|
| 2076 |
+
"num_train_epochs": 16,
|
| 2077 |
+
"save_steps": 400,
|
| 2078 |
+
"total_flos": 0.0,
|
| 2079 |
+
"train_batch_size": 1,
|
| 2080 |
+
"trial_name": null,
|
| 2081 |
+
"trial_params": null
|
| 2082 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d10cade09e8662424df8edaf4dc955c1a689008be350250b395adaf9f52b6d
|
| 3 |
+
size 7032
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
+
|
| 15 |
+
import argparse
|
| 16 |
+
import torch
|
| 17 |
+
import glob
|
| 18 |
+
import math
|
| 19 |
+
import os
|
| 20 |
+
import re
|
| 21 |
+
from collections import OrderedDict
|
| 22 |
+
from dataclasses import dataclass
|
| 23 |
+
|
| 24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
+
from deepspeed.utils import logger
|
| 27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
@dataclass
|
| 33 |
+
class zero_model_state:
|
| 34 |
+
buffers: dict()
|
| 35 |
+
param_shapes: dict()
|
| 36 |
+
shared_params: list
|
| 37 |
+
ds_version: int
|
| 38 |
+
frozen_param_shapes: dict()
|
| 39 |
+
frozen_param_fragments: dict()
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
debug = 0
|
| 43 |
+
|
| 44 |
+
# load to cpu
|
| 45 |
+
device = torch.device('cpu')
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def atoi(text):
|
| 49 |
+
return int(text) if text.isdigit() else text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def natural_keys(text):
|
| 53 |
+
'''
|
| 54 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
+
(See Toothy's implementation in the comments)
|
| 57 |
+
'''
|
| 58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
+
if not os.path.isdir(checkpoint_dir):
|
| 63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
+
|
| 65 |
+
# there should be only one file
|
| 66 |
+
if zero_stage <= 2:
|
| 67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
+
elif zero_stage == 3:
|
| 69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
+
|
| 71 |
+
if not os.path.exists(file):
|
| 72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
+
|
| 74 |
+
return file
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
+
|
| 81 |
+
if len(ckpt_files) == 0:
|
| 82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
+
|
| 84 |
+
return ckpt_files
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def get_optim_files(checkpoint_dir):
|
| 88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def get_model_state_files(checkpoint_dir):
|
| 92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def parse_model_states(files):
|
| 96 |
+
zero_model_states = []
|
| 97 |
+
for file in files:
|
| 98 |
+
state_dict = torch.load(file, map_location=device)
|
| 99 |
+
|
| 100 |
+
if BUFFER_NAMES not in state_dict:
|
| 101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
+
if debug:
|
| 104 |
+
print("Found buffers:", buffer_names)
|
| 105 |
+
|
| 106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
+
|
| 110 |
+
# collect parameters that are included in param_shapes
|
| 111 |
+
param_names = []
|
| 112 |
+
for s in param_shapes:
|
| 113 |
+
for name in s.keys():
|
| 114 |
+
param_names.append(name)
|
| 115 |
+
|
| 116 |
+
# update with frozen parameters
|
| 117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
+
if frozen_param_shapes is not None:
|
| 119 |
+
if debug:
|
| 120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
+
param_names += list(frozen_param_shapes.keys())
|
| 122 |
+
|
| 123 |
+
# handle shared params
|
| 124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
+
|
| 126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
+
|
| 128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
+
|
| 130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
+
param_shapes=param_shapes,
|
| 132 |
+
shared_params=shared_params,
|
| 133 |
+
ds_version=ds_version,
|
| 134 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
+
zero_model_states.append(z_model_state)
|
| 137 |
+
|
| 138 |
+
return zero_model_states
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
+
|
| 143 |
+
total_files = len(files)
|
| 144 |
+
state_dicts = []
|
| 145 |
+
for f in files:
|
| 146 |
+
state_dict = torch.load(f, map_location=device)
|
| 147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 148 |
+
# and also handle the case where it was already removed by another helper script
|
| 149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 150 |
+
state_dicts.append(state_dict)
|
| 151 |
+
|
| 152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 156 |
+
|
| 157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 159 |
+
# use the max of the partition_count to get the dp world_size.
|
| 160 |
+
|
| 161 |
+
if type(world_size) is list:
|
| 162 |
+
world_size = max(world_size)
|
| 163 |
+
|
| 164 |
+
if world_size != total_files:
|
| 165 |
+
raise ValueError(
|
| 166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 168 |
+
)
|
| 169 |
+
|
| 170 |
+
# the groups are named differently in each stage
|
| 171 |
+
if zero_stage <= 2:
|
| 172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 173 |
+
elif zero_stage == 3:
|
| 174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 175 |
+
else:
|
| 176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 177 |
+
|
| 178 |
+
if zero_stage <= 2:
|
| 179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 180 |
+
elif zero_stage == 3:
|
| 181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 183 |
+
#
|
| 184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 186 |
+
|
| 187 |
+
fp32_flat_groups = [
|
| 188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 189 |
+
]
|
| 190 |
+
|
| 191 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 195 |
+
"""
|
| 196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 197 |
+
|
| 198 |
+
Args:
|
| 199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 200 |
+
|
| 201 |
+
"""
|
| 202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 203 |
+
|
| 204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 207 |
+
|
| 208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 209 |
+
|
| 210 |
+
zero_model_states = parse_model_states(model_files)
|
| 211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 212 |
+
|
| 213 |
+
if zero_stage <= 2:
|
| 214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 215 |
+
exclude_frozen_parameters)
|
| 216 |
+
elif zero_stage == 3:
|
| 217 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 218 |
+
exclude_frozen_parameters)
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 222 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 223 |
+
return
|
| 224 |
+
|
| 225 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 226 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 227 |
+
|
| 228 |
+
if debug:
|
| 229 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 230 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 231 |
+
|
| 232 |
+
wanted_params = len(frozen_param_shapes)
|
| 233 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 235 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 236 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 237 |
+
|
| 238 |
+
total_params = 0
|
| 239 |
+
total_numel = 0
|
| 240 |
+
for name, shape in frozen_param_shapes.items():
|
| 241 |
+
total_params += 1
|
| 242 |
+
unpartitioned_numel = shape.numel()
|
| 243 |
+
total_numel += unpartitioned_numel
|
| 244 |
+
|
| 245 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 246 |
+
|
| 247 |
+
if debug:
|
| 248 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 249 |
+
|
| 250 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 251 |
+
|
| 252 |
+
|
| 253 |
+
def _has_callable(obj, fn):
|
| 254 |
+
attr = getattr(obj, fn, None)
|
| 255 |
+
return callable(attr)
|
| 256 |
+
|
| 257 |
+
|
| 258 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 259 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 260 |
+
|
| 261 |
+
# Reconstruction protocol:
|
| 262 |
+
#
|
| 263 |
+
# XXX: document this
|
| 264 |
+
|
| 265 |
+
if debug:
|
| 266 |
+
for i in range(world_size):
|
| 267 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 268 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 269 |
+
|
| 270 |
+
# XXX: memory usage doubles here (zero2)
|
| 271 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 272 |
+
merged_single_partition_of_fp32_groups = []
|
| 273 |
+
for i in range(num_param_groups):
|
| 274 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 275 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 276 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 277 |
+
avail_numel = sum(
|
| 278 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 279 |
+
|
| 280 |
+
if debug:
|
| 281 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 282 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 283 |
+
# not asserting if there is a mismatch due to possible padding
|
| 284 |
+
print(f"Have {avail_numel} numels to process.")
|
| 285 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 286 |
+
|
| 287 |
+
# params
|
| 288 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 289 |
+
# out-of-core computing solution
|
| 290 |
+
total_numel = 0
|
| 291 |
+
total_params = 0
|
| 292 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 293 |
+
offset = 0
|
| 294 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 295 |
+
for name, shape in shapes.items():
|
| 296 |
+
|
| 297 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 298 |
+
total_numel += unpartitioned_numel
|
| 299 |
+
total_params += 1
|
| 300 |
+
|
| 301 |
+
if debug:
|
| 302 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 303 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 304 |
+
offset += unpartitioned_numel
|
| 305 |
+
|
| 306 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 307 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 308 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 309 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 310 |
+
align_to = 2 * world_size
|
| 311 |
+
|
| 312 |
+
def zero2_align(x):
|
| 313 |
+
return align_to * math.ceil(x / align_to)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
offset = zero2_align(offset)
|
| 319 |
+
avail_numel = zero2_align(avail_numel)
|
| 320 |
+
|
| 321 |
+
if debug:
|
| 322 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 323 |
+
|
| 324 |
+
# Sanity check
|
| 325 |
+
if offset != avail_numel:
|
| 326 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 327 |
+
|
| 328 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 329 |
+
|
| 330 |
+
|
| 331 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 332 |
+
exclude_frozen_parameters):
|
| 333 |
+
state_dict = OrderedDict()
|
| 334 |
+
|
| 335 |
+
# buffers
|
| 336 |
+
buffers = zero_model_states[0].buffers
|
| 337 |
+
state_dict.update(buffers)
|
| 338 |
+
if debug:
|
| 339 |
+
print(f"added {len(buffers)} buffers")
|
| 340 |
+
|
| 341 |
+
if not exclude_frozen_parameters:
|
| 342 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 343 |
+
|
| 344 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 345 |
+
|
| 346 |
+
# recover shared parameters
|
| 347 |
+
for pair in zero_model_states[0].shared_params:
|
| 348 |
+
if pair[1] in state_dict:
|
| 349 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 350 |
+
|
| 351 |
+
return state_dict
|
| 352 |
+
|
| 353 |
+
|
| 354 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 355 |
+
remainder = unpartitioned_numel % world_size
|
| 356 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 357 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 358 |
+
return partitioned_numel, padding_numel
|
| 359 |
+
|
| 360 |
+
|
| 361 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 362 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 363 |
+
return
|
| 364 |
+
|
| 365 |
+
if debug:
|
| 366 |
+
for i in range(world_size):
|
| 367 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 368 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 369 |
+
|
| 370 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 371 |
+
wanted_params = len(frozen_param_shapes)
|
| 372 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 373 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 374 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 375 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 376 |
+
|
| 377 |
+
total_params = 0
|
| 378 |
+
total_numel = 0
|
| 379 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 380 |
+
total_params += 1
|
| 381 |
+
unpartitioned_numel = shape.numel()
|
| 382 |
+
total_numel += unpartitioned_numel
|
| 383 |
+
|
| 384 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 385 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 386 |
+
|
| 387 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 388 |
+
|
| 389 |
+
if debug:
|
| 390 |
+
print(
|
| 391 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 392 |
+
)
|
| 393 |
+
|
| 394 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 395 |
+
|
| 396 |
+
|
| 397 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 398 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 399 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 400 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 401 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 402 |
+
|
| 403 |
+
# merge list of dicts, preserving order
|
| 404 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 405 |
+
|
| 406 |
+
if debug:
|
| 407 |
+
for i in range(world_size):
|
| 408 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 409 |
+
|
| 410 |
+
wanted_params = len(param_shapes)
|
| 411 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 412 |
+
# not asserting if there is a mismatch due to possible padding
|
| 413 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 414 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 415 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 416 |
+
|
| 417 |
+
# params
|
| 418 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 419 |
+
# out-of-core computing solution
|
| 420 |
+
offset = 0
|
| 421 |
+
total_numel = 0
|
| 422 |
+
total_params = 0
|
| 423 |
+
for name, shape in param_shapes.items():
|
| 424 |
+
|
| 425 |
+
unpartitioned_numel = shape.numel()
|
| 426 |
+
total_numel += unpartitioned_numel
|
| 427 |
+
total_params += 1
|
| 428 |
+
|
| 429 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 430 |
+
|
| 431 |
+
if debug:
|
| 432 |
+
print(
|
| 433 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 434 |
+
)
|
| 435 |
+
|
| 436 |
+
# XXX: memory usage doubles here
|
| 437 |
+
state_dict[name] = torch.cat(
|
| 438 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 439 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 440 |
+
offset += partitioned_numel
|
| 441 |
+
|
| 442 |
+
offset *= world_size
|
| 443 |
+
|
| 444 |
+
# Sanity check
|
| 445 |
+
if offset != avail_numel:
|
| 446 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 447 |
+
|
| 448 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 449 |
+
|
| 450 |
+
|
| 451 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 452 |
+
exclude_frozen_parameters):
|
| 453 |
+
state_dict = OrderedDict()
|
| 454 |
+
|
| 455 |
+
# buffers
|
| 456 |
+
buffers = zero_model_states[0].buffers
|
| 457 |
+
state_dict.update(buffers)
|
| 458 |
+
if debug:
|
| 459 |
+
print(f"added {len(buffers)} buffers")
|
| 460 |
+
|
| 461 |
+
if not exclude_frozen_parameters:
|
| 462 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 463 |
+
|
| 464 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 465 |
+
|
| 466 |
+
# recover shared parameters
|
| 467 |
+
for pair in zero_model_states[0].shared_params:
|
| 468 |
+
if pair[1] in state_dict:
|
| 469 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 470 |
+
|
| 471 |
+
return state_dict
|
| 472 |
+
|
| 473 |
+
|
| 474 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 475 |
+
"""
|
| 476 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 477 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 478 |
+
via a model hub.
|
| 479 |
+
|
| 480 |
+
Args:
|
| 481 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 482 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 483 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 484 |
+
|
| 485 |
+
Returns:
|
| 486 |
+
- pytorch ``state_dict``
|
| 487 |
+
|
| 488 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 489 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 490 |
+
the checkpoint.
|
| 491 |
+
|
| 492 |
+
A typical usage might be ::
|
| 493 |
+
|
| 494 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 495 |
+
# do the training and checkpoint saving
|
| 496 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 497 |
+
model = model.cpu() # move to cpu
|
| 498 |
+
model.load_state_dict(state_dict)
|
| 499 |
+
# submit to model hub or save the model to share with others
|
| 500 |
+
|
| 501 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 502 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 503 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 504 |
+
|
| 505 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 506 |
+
|
| 507 |
+
"""
|
| 508 |
+
if tag is None:
|
| 509 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 510 |
+
if os.path.isfile(latest_path):
|
| 511 |
+
with open(latest_path, 'r') as fd:
|
| 512 |
+
tag = fd.read().strip()
|
| 513 |
+
else:
|
| 514 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 515 |
+
|
| 516 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 517 |
+
|
| 518 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 519 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 520 |
+
|
| 521 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
| 525 |
+
"""
|
| 526 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 527 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 528 |
+
|
| 529 |
+
Args:
|
| 530 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 531 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 532 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 533 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 534 |
+
"""
|
| 535 |
+
|
| 536 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 537 |
+
print(f"Saving fp32 state dict to {output_file}")
|
| 538 |
+
torch.save(state_dict, output_file)
|
| 539 |
+
|
| 540 |
+
|
| 541 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 542 |
+
"""
|
| 543 |
+
1. Put the provided model to cpu
|
| 544 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 545 |
+
3. Load it into the provided model
|
| 546 |
+
|
| 547 |
+
Args:
|
| 548 |
+
- ``model``: the model object to update
|
| 549 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 550 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 551 |
+
|
| 552 |
+
Returns:
|
| 553 |
+
- ``model`: modified model
|
| 554 |
+
|
| 555 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 556 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 557 |
+
conveniently placed for you in the checkpoint folder.
|
| 558 |
+
|
| 559 |
+
A typical usage might be ::
|
| 560 |
+
|
| 561 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 562 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 563 |
+
# submit to model hub or save the model to share with others
|
| 564 |
+
|
| 565 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 566 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 567 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 568 |
+
|
| 569 |
+
"""
|
| 570 |
+
logger.info(f"Extracting fp32 weights")
|
| 571 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 572 |
+
|
| 573 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 574 |
+
model = model.cpu()
|
| 575 |
+
model.load_state_dict(state_dict, strict=False)
|
| 576 |
+
|
| 577 |
+
return model
|
| 578 |
+
|
| 579 |
+
|
| 580 |
+
if __name__ == "__main__":
|
| 581 |
+
|
| 582 |
+
parser = argparse.ArgumentParser()
|
| 583 |
+
parser.add_argument("checkpoint_dir",
|
| 584 |
+
type=str,
|
| 585 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 586 |
+
parser.add_argument(
|
| 587 |
+
"output_file",
|
| 588 |
+
type=str,
|
| 589 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 590 |
+
parser.add_argument("-t",
|
| 591 |
+
"--tag",
|
| 592 |
+
type=str,
|
| 593 |
+
default=None,
|
| 594 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 595 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 596 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 597 |
+
args = parser.parse_args()
|
| 598 |
+
|
| 599 |
+
debug = args.debug
|
| 600 |
+
|
| 601 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 602 |
+
args.output_file,
|
| 603 |
+
tag=args.tag,
|
| 604 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|