Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +30 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +69 -0
- trainer_state.json +633 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endofprompt|>": 100276,
|
| 3 |
+
"<|im_end|>": 100265,
|
| 4 |
+
"<|im_start|>": 100264
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"model_type": "phi",
|
| 17 |
+
"num_attention_heads": 24,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"partial_rotary_factor": 0.4,
|
| 21 |
+
"qk_layernorm": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.41.0.dev0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 100263
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"transformers_version": "4.41.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f3afa67fadbf1fe9bae2ed05e5f8571d22ff920efd64fecaf1e0a94f72e017
|
| 3 |
+
size 767605596
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:142a051422b7e1112ebf8bba13a9c035529e012828803d3ef00dc89bf6ee757b
|
| 3 |
+
size 1535267130
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:147b23f854f774000afa091253a137b49984d95ce2714ad8c5a33070b3ddc501
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d228bf63f83d5832d490902a654b84e48391ec159f69749952b98ac8512cff53
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100257": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"100258": {
|
| 13 |
+
"content": "<|fim_prefix|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100259": {
|
| 21 |
+
"content": "<|fim_middle|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100260": {
|
| 29 |
+
"content": "<|fim_suffix|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100264": {
|
| 37 |
+
"content": "<|im_start|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100265": {
|
| 45 |
+
"content": "<|im_end|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"100276": {
|
| 53 |
+
"content": "<|endofprompt|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"bos_token": "<|endoftext|>",
|
| 62 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 63 |
+
"clean_up_tokenization_spaces": false,
|
| 64 |
+
"eos_token": "<|endoftext|>",
|
| 65 |
+
"model_max_length": 8192,
|
| 66 |
+
"pad_token": "<|endoftext|>",
|
| 67 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 68 |
+
"unk_token": "<|endoftext|>"
|
| 69 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.010214409722222,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 36000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0086102430555555,
|
| 13 |
+
"grad_norm": 0.3148804008960724,
|
| 14 |
+
"learning_rate": 0.0009998758966336297,
|
| 15 |
+
"loss": 5.1098,
|
| 16 |
+
"num_input_tokens_seen": 521485760,
|
| 17 |
+
"step": 1000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0086102430555555,
|
| 21 |
+
"eval_loss": 4.390458106994629,
|
| 22 |
+
"eval_runtime": 157.9404,
|
| 23 |
+
"eval_samples_per_second": 116.5,
|
| 24 |
+
"eval_steps_per_second": 7.281,
|
| 25 |
+
"num_input_tokens_seen": 521485760,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0169140625,
|
| 30 |
+
"grad_norm": 0.24177567660808563,
|
| 31 |
+
"learning_rate": 0.0009969004950996173,
|
| 32 |
+
"loss": 3.7649,
|
| 33 |
+
"num_input_tokens_seen": 1042810727,
|
| 34 |
+
"step": 2000
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0169140625,
|
| 38 |
+
"eval_loss": 4.018285274505615,
|
| 39 |
+
"eval_runtime": 157.619,
|
| 40 |
+
"eval_samples_per_second": 116.737,
|
| 41 |
+
"eval_steps_per_second": 7.296,
|
| 42 |
+
"num_input_tokens_seen": 1042810727,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 4.006030381944444,
|
| 47 |
+
"grad_norm": 0.22102612257003784,
|
| 48 |
+
"learning_rate": 0.0009899808525182935,
|
| 49 |
+
"loss": 3.3244,
|
| 50 |
+
"num_input_tokens_seen": 1564614407,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.006030381944444,
|
| 55 |
+
"eval_loss": 3.883763074874878,
|
| 56 |
+
"eval_runtime": 158.112,
|
| 57 |
+
"eval_samples_per_second": 116.373,
|
| 58 |
+
"eval_steps_per_second": 7.273,
|
| 59 |
+
"num_input_tokens_seen": 1564614407,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 5.0143046875,
|
| 64 |
+
"grad_norm": 0.25155559182167053,
|
| 65 |
+
"learning_rate": 0.0009791718948528457,
|
| 66 |
+
"loss": 3.2291,
|
| 67 |
+
"num_input_tokens_seen": 2086545237,
|
| 68 |
+
"step": 4000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0143046875,
|
| 72 |
+
"eval_loss": 3.7907443046569824,
|
| 73 |
+
"eval_runtime": 157.3668,
|
| 74 |
+
"eval_samples_per_second": 116.924,
|
| 75 |
+
"eval_steps_per_second": 7.308,
|
| 76 |
+
"num_input_tokens_seen": 2086545237,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.002637152777778,
|
| 81 |
+
"grad_norm": 0.23016224801540375,
|
| 82 |
+
"learning_rate": 0.0009645594202357438,
|
| 83 |
+
"loss": 3.1779,
|
| 84 |
+
"num_input_tokens_seen": 2608572303,
|
| 85 |
+
"step": 5000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 7.002637152777778,
|
| 89 |
+
"eval_loss": 3.7254457473754883,
|
| 90 |
+
"eval_runtime": 158.0679,
|
| 91 |
+
"eval_samples_per_second": 116.406,
|
| 92 |
+
"eval_steps_per_second": 7.275,
|
| 93 |
+
"num_input_tokens_seen": 2608572303,
|
| 94 |
+
"step": 5000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 8.010796006944444,
|
| 98 |
+
"grad_norm": 0.1911187618970871,
|
| 99 |
+
"learning_rate": 0.0009462594179299406,
|
| 100 |
+
"loss": 3.1106,
|
| 101 |
+
"num_input_tokens_seen": 3130451615,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.010796006944444,
|
| 106 |
+
"eval_loss": 3.6576924324035645,
|
| 107 |
+
"eval_runtime": 156.4171,
|
| 108 |
+
"eval_samples_per_second": 117.634,
|
| 109 |
+
"eval_steps_per_second": 7.352,
|
| 110 |
+
"num_input_tokens_seen": 3130451615,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 9.0191015625,
|
| 115 |
+
"grad_norm": 0.24357692897319794,
|
| 116 |
+
"learning_rate": 0.0009244171476423036,
|
| 117 |
+
"loss": 3.0493,
|
| 118 |
+
"num_input_tokens_seen": 3652271439,
|
| 119 |
+
"step": 7000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 9.0191015625,
|
| 123 |
+
"eval_loss": 3.6375908851623535,
|
| 124 |
+
"eval_runtime": 157.211,
|
| 125 |
+
"eval_samples_per_second": 117.04,
|
| 126 |
+
"eval_steps_per_second": 7.315,
|
| 127 |
+
"num_input_tokens_seen": 3652271439,
|
| 128 |
+
"step": 7000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0083489583333334,
|
| 132 |
+
"grad_norm": 0.17816534638404846,
|
| 133 |
+
"learning_rate": 0.0008992059864973972,
|
| 134 |
+
"loss": 3.0005,
|
| 135 |
+
"num_input_tokens_seen": 4174145711,
|
| 136 |
+
"step": 8000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.0083489583333334,
|
| 140 |
+
"eval_loss": 3.5855612754821777,
|
| 141 |
+
"eval_runtime": 155.3476,
|
| 142 |
+
"eval_samples_per_second": 118.444,
|
| 143 |
+
"eval_steps_per_second": 7.403,
|
| 144 |
+
"num_input_tokens_seen": 4174145711,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.016631076388889,
|
| 149 |
+
"grad_norm": 0.1740865856409073,
|
| 150 |
+
"learning_rate": 0.0008708260528239789,
|
| 151 |
+
"loss": 3.0155,
|
| 152 |
+
"num_input_tokens_seen": 4696186623,
|
| 153 |
+
"step": 9000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.016631076388889,
|
| 157 |
+
"eval_loss": 3.580111265182495,
|
| 158 |
+
"eval_runtime": 154.9402,
|
| 159 |
+
"eval_samples_per_second": 118.755,
|
| 160 |
+
"eval_steps_per_second": 7.422,
|
| 161 |
+
"num_input_tokens_seen": 4696186623,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.005178819444445,
|
| 166 |
+
"grad_norm": 0.19117484986782074,
|
| 167 |
+
"learning_rate": 0.0008395026176781626,
|
| 168 |
+
"loss": 2.9609,
|
| 169 |
+
"num_input_tokens_seen": 5217948966,
|
| 170 |
+
"step": 10000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.005178819444445,
|
| 174 |
+
"eval_loss": 3.5479941368103027,
|
| 175 |
+
"eval_runtime": 154.297,
|
| 176 |
+
"eval_samples_per_second": 119.251,
|
| 177 |
+
"eval_steps_per_second": 7.453,
|
| 178 |
+
"num_input_tokens_seen": 5217948966,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.013779513888889,
|
| 183 |
+
"grad_norm": 0.16193148493766785,
|
| 184 |
+
"learning_rate": 0.0008054843167120826,
|
| 185 |
+
"loss": 2.9376,
|
| 186 |
+
"num_input_tokens_seen": 5739503318,
|
| 187 |
+
"step": 11000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 5.013779513888889,
|
| 191 |
+
"eval_loss": 3.5245985984802246,
|
| 192 |
+
"eval_runtime": 154.2866,
|
| 193 |
+
"eval_samples_per_second": 119.259,
|
| 194 |
+
"eval_steps_per_second": 7.454,
|
| 195 |
+
"num_input_tokens_seen": 5739503318,
|
| 196 |
+
"step": 11000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 7.002284722222222,
|
| 200 |
+
"grad_norm": 0.16273680329322815,
|
| 201 |
+
"learning_rate": 0.0007690411765816864,
|
| 202 |
+
"loss": 2.9641,
|
| 203 |
+
"num_input_tokens_seen": 6261603062,
|
| 204 |
+
"step": 12000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.002284722222222,
|
| 208 |
+
"eval_loss": 3.5051820278167725,
|
| 209 |
+
"eval_runtime": 153.5212,
|
| 210 |
+
"eval_samples_per_second": 119.853,
|
| 211 |
+
"eval_steps_per_second": 7.491,
|
| 212 |
+
"num_input_tokens_seen": 6261603062,
|
| 213 |
+
"step": 12000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.010577256944444,
|
| 217 |
+
"grad_norm": 0.1603420227766037,
|
| 218 |
+
"learning_rate": 0.0007304624715594139,
|
| 219 |
+
"loss": 2.9166,
|
| 220 |
+
"num_input_tokens_seen": 6783593829,
|
| 221 |
+
"step": 13000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 8.010577256944444,
|
| 225 |
+
"eval_loss": 3.497760772705078,
|
| 226 |
+
"eval_runtime": 153.4387,
|
| 227 |
+
"eval_samples_per_second": 119.918,
|
| 228 |
+
"eval_steps_per_second": 7.495,
|
| 229 |
+
"num_input_tokens_seen": 6783593829,
|
| 230 |
+
"step": 13000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.018918402777778,
|
| 234 |
+
"grad_norm": 0.1665274053812027,
|
| 235 |
+
"learning_rate": 0.0006900544273653075,
|
| 236 |
+
"loss": 2.8821,
|
| 237 |
+
"num_input_tokens_seen": 7305434352,
|
| 238 |
+
"step": 14000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 9.018918402777778,
|
| 242 |
+
"eval_loss": 3.4890758991241455,
|
| 243 |
+
"eval_runtime": 153.9326,
|
| 244 |
+
"eval_samples_per_second": 119.533,
|
| 245 |
+
"eval_steps_per_second": 7.471,
|
| 246 |
+
"num_input_tokens_seen": 7305434352,
|
| 247 |
+
"step": 14000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.0083055555555556,
|
| 251 |
+
"grad_norm": 0.16452226042747498,
|
| 252 |
+
"learning_rate": 0.000648137790442817,
|
| 253 |
+
"loss": 2.8766,
|
| 254 |
+
"num_input_tokens_seen": 7827274720,
|
| 255 |
+
"step": 15000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0083055555555556,
|
| 259 |
+
"eval_loss": 3.4698522090911865,
|
| 260 |
+
"eval_runtime": 153.8232,
|
| 261 |
+
"eval_samples_per_second": 119.618,
|
| 262 |
+
"eval_steps_per_second": 7.476,
|
| 263 |
+
"num_input_tokens_seen": 7827274720,
|
| 264 |
+
"step": 15000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.0166302083333334,
|
| 268 |
+
"grad_norm": 0.17168712615966797,
|
| 269 |
+
"learning_rate": 0.0006050452819736389,
|
| 270 |
+
"loss": 2.8809,
|
| 271 |
+
"num_input_tokens_seen": 8348682560,
|
| 272 |
+
"step": 16000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.0166302083333334,
|
| 276 |
+
"eval_loss": 3.4530444145202637,
|
| 277 |
+
"eval_runtime": 152.7846,
|
| 278 |
+
"eval_samples_per_second": 120.431,
|
| 279 |
+
"eval_steps_per_second": 7.527,
|
| 280 |
+
"num_input_tokens_seen": 8348682560,
|
| 281 |
+
"step": 16000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.005391493055556,
|
| 285 |
+
"grad_norm": 0.16454088687896729,
|
| 286 |
+
"learning_rate": 0.0005611189568408173,
|
| 287 |
+
"loss": 2.885,
|
| 288 |
+
"num_input_tokens_seen": 8870476792,
|
| 289 |
+
"step": 17000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.005391493055556,
|
| 293 |
+
"eval_loss": 3.442610025405884,
|
| 294 |
+
"eval_runtime": 153.4312,
|
| 295 |
+
"eval_samples_per_second": 119.923,
|
| 296 |
+
"eval_steps_per_second": 7.495,
|
| 297 |
+
"num_input_tokens_seen": 8870476792,
|
| 298 |
+
"step": 17000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 5.013413194444444,
|
| 302 |
+
"grad_norm": 0.1566428244113922,
|
| 303 |
+
"learning_rate": 0.0005167074885038374,
|
| 304 |
+
"loss": 2.8616,
|
| 305 |
+
"num_input_tokens_seen": 9392395768,
|
| 306 |
+
"step": 18000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.013413194444444,
|
| 310 |
+
"eval_loss": 3.4214282035827637,
|
| 311 |
+
"eval_runtime": 153.1872,
|
| 312 |
+
"eval_samples_per_second": 120.115,
|
| 313 |
+
"eval_steps_per_second": 7.507,
|
| 314 |
+
"num_input_tokens_seen": 9392395768,
|
| 315 |
+
"step": 18000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 7.001969618055556,
|
| 319 |
+
"grad_norm": 0.16596154868602753,
|
| 320 |
+
"learning_rate": 0.000472163401337526,
|
| 321 |
+
"loss": 2.8546,
|
| 322 |
+
"num_input_tokens_seen": 9914322356,
|
| 323 |
+
"step": 19000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 7.001969618055556,
|
| 327 |
+
"eval_loss": 3.399761438369751,
|
| 328 |
+
"eval_runtime": 153.8483,
|
| 329 |
+
"eval_samples_per_second": 119.598,
|
| 330 |
+
"eval_steps_per_second": 7.475,
|
| 331 |
+
"num_input_tokens_seen": 9914322356,
|
| 332 |
+
"step": 19000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.010303819444445,
|
| 336 |
+
"grad_norm": 0.16305798292160034,
|
| 337 |
+
"learning_rate": 0.00042784027240358674,
|
| 338 |
+
"loss": 2.8039,
|
| 339 |
+
"num_input_tokens_seen": 10436233756,
|
| 340 |
+
"step": 20000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.010303819444445,
|
| 344 |
+
"eval_loss": 3.3940844535827637,
|
| 345 |
+
"eval_runtime": 158.2602,
|
| 346 |
+
"eval_samples_per_second": 116.264,
|
| 347 |
+
"eval_steps_per_second": 7.267,
|
| 348 |
+
"num_input_tokens_seen": 10436233756,
|
| 349 |
+
"step": 20000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.0082630208333334,
|
| 353 |
+
"grad_norm": 0.2344750463962555,
|
| 354 |
+
"learning_rate": 0.00038408992486623584,
|
| 355 |
+
"loss": 2.7959,
|
| 356 |
+
"num_input_tokens_seen": 10958156105,
|
| 357 |
+
"step": 21000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.0082630208333334,
|
| 361 |
+
"eval_loss": 3.4070310592651367,
|
| 362 |
+
"eval_runtime": 155.4587,
|
| 363 |
+
"eval_samples_per_second": 118.359,
|
| 364 |
+
"eval_steps_per_second": 7.397,
|
| 365 |
+
"num_input_tokens_seen": 10958156105,
|
| 366 |
+
"step": 21000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.0165078125,
|
| 370 |
+
"grad_norm": 0.16524210572242737,
|
| 371 |
+
"learning_rate": 0.0003412596353297288,
|
| 372 |
+
"loss": 2.791,
|
| 373 |
+
"num_input_tokens_seen": 11479508780,
|
| 374 |
+
"step": 22000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.0165078125,
|
| 378 |
+
"eval_loss": 3.3836262226104736,
|
| 379 |
+
"eval_runtime": 155.5662,
|
| 380 |
+
"eval_samples_per_second": 118.278,
|
| 381 |
+
"eval_steps_per_second": 7.392,
|
| 382 |
+
"num_input_tokens_seen": 11479508780,
|
| 383 |
+
"step": 22000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.005475694444445,
|
| 387 |
+
"grad_norm": 0.18112713098526,
|
| 388 |
+
"learning_rate": 0.0002996893772650602,
|
| 389 |
+
"loss": 2.7732,
|
| 390 |
+
"num_input_tokens_seen": 12001335662,
|
| 391 |
+
"step": 23000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 4.005475694444445,
|
| 395 |
+
"eval_loss": 3.374772548675537,
|
| 396 |
+
"eval_runtime": 158.5198,
|
| 397 |
+
"eval_samples_per_second": 116.074,
|
| 398 |
+
"eval_steps_per_second": 7.255,
|
| 399 |
+
"num_input_tokens_seen": 12001335662,
|
| 400 |
+
"step": 23000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 5.013543402777778,
|
| 404 |
+
"grad_norm": 0.20000149309635162,
|
| 405 |
+
"learning_rate": 0.0002597091224066581,
|
| 406 |
+
"loss": 2.776,
|
| 407 |
+
"num_input_tokens_seen": 12523295262,
|
| 408 |
+
"step": 24000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.013543402777778,
|
| 412 |
+
"eval_loss": 3.3714466094970703,
|
| 413 |
+
"eval_runtime": 156.2603,
|
| 414 |
+
"eval_samples_per_second": 117.752,
|
| 415 |
+
"eval_steps_per_second": 7.36,
|
| 416 |
+
"num_input_tokens_seen": 12523295262,
|
| 417 |
+
"step": 24000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.0082881944444444,
|
| 421 |
+
"grad_norm": 0.17906545102596283,
|
| 422 |
+
"learning_rate": 0.0002216362215397393,
|
| 423 |
+
"loss": 2.7496,
|
| 424 |
+
"num_input_tokens_seen": 13045103310,
|
| 425 |
+
"step": 25000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.0082881944444444,
|
| 429 |
+
"eval_loss": 3.3571267127990723,
|
| 430 |
+
"eval_runtime": 156.601,
|
| 431 |
+
"eval_samples_per_second": 117.496,
|
| 432 |
+
"eval_steps_per_second": 7.344,
|
| 433 |
+
"num_input_tokens_seen": 13045103310,
|
| 434 |
+
"step": 25000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.0165208333333333,
|
| 438 |
+
"grad_norm": 0.17018218338489532,
|
| 439 |
+
"learning_rate": 0.00018577288546882165,
|
| 440 |
+
"loss": 2.7435,
|
| 441 |
+
"num_input_tokens_seen": 13566410636,
|
| 442 |
+
"step": 26000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.0165208333333333,
|
| 446 |
+
"eval_loss": 3.3441579341888428,
|
| 447 |
+
"eval_runtime": 157.974,
|
| 448 |
+
"eval_samples_per_second": 116.475,
|
| 449 |
+
"eval_steps_per_second": 7.28,
|
| 450 |
+
"num_input_tokens_seen": 13566410636,
|
| 451 |
+
"step": 26000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 4.005661458333333,
|
| 455 |
+
"grad_norm": 0.16987864673137665,
|
| 456 |
+
"learning_rate": 0.00015240378616267886,
|
| 457 |
+
"loss": 2.7321,
|
| 458 |
+
"num_input_tokens_seen": 14088234739,
|
| 459 |
+
"step": 27000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.005661458333333,
|
| 463 |
+
"eval_loss": 3.335869550704956,
|
| 464 |
+
"eval_runtime": 156.5095,
|
| 465 |
+
"eval_samples_per_second": 117.565,
|
| 466 |
+
"eval_steps_per_second": 7.348,
|
| 467 |
+
"num_input_tokens_seen": 14088234739,
|
| 468 |
+
"step": 27000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 5.013948784722222,
|
| 472 |
+
"grad_norm": 0.18387989699840546,
|
| 473 |
+
"learning_rate": 0.00012179379711709738,
|
| 474 |
+
"loss": 2.7137,
|
| 475 |
+
"num_input_tokens_seen": 14609933027,
|
| 476 |
+
"step": 28000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.013948784722222,
|
| 480 |
+
"eval_loss": 3.323387861251831,
|
| 481 |
+
"eval_runtime": 156.9047,
|
| 482 |
+
"eval_samples_per_second": 117.269,
|
| 483 |
+
"eval_steps_per_second": 7.329,
|
| 484 |
+
"num_input_tokens_seen": 14609933027,
|
| 485 |
+
"step": 28000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.002777777777778,
|
| 489 |
+
"grad_norm": 0.17292186617851257,
|
| 490 |
+
"learning_rate": 9.418589087173441e-05,
|
| 491 |
+
"loss": 2.7152,
|
| 492 |
+
"num_input_tokens_seen": 15131802301,
|
| 493 |
+
"step": 29000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 7.002777777777778,
|
| 497 |
+
"eval_loss": 3.318844795227051,
|
| 498 |
+
"eval_runtime": 156.7029,
|
| 499 |
+
"eval_samples_per_second": 117.42,
|
| 500 |
+
"eval_steps_per_second": 7.339,
|
| 501 |
+
"num_input_tokens_seen": 15131802301,
|
| 502 |
+
"step": 29000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 8.0111015625,
|
| 506 |
+
"grad_norm": 0.17619270086288452,
|
| 507 |
+
"learning_rate": 6.979921036993042e-05,
|
| 508 |
+
"loss": 2.7042,
|
| 509 |
+
"num_input_tokens_seen": 15653732413,
|
| 510 |
+
"step": 30000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 8.0111015625,
|
| 514 |
+
"eval_loss": 3.3149850368499756,
|
| 515 |
+
"eval_runtime": 157.8074,
|
| 516 |
+
"eval_samples_per_second": 116.598,
|
| 517 |
+
"eval_steps_per_second": 7.287,
|
| 518 |
+
"num_input_tokens_seen": 15653732413,
|
| 519 |
+
"step": 30000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.0080494791666668,
|
| 523 |
+
"grad_norm": 0.20021264255046844,
|
| 524 |
+
"learning_rate": 4.882732947041818e-05,
|
| 525 |
+
"loss": 2.7114,
|
| 526 |
+
"num_input_tokens_seen": 16175778125,
|
| 527 |
+
"step": 31000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0080494791666668,
|
| 531 |
+
"eval_loss": 3.3138480186462402,
|
| 532 |
+
"eval_runtime": 155.6732,
|
| 533 |
+
"eval_samples_per_second": 118.196,
|
| 534 |
+
"eval_steps_per_second": 7.387,
|
| 535 |
+
"num_input_tokens_seen": 16175778125,
|
| 536 |
+
"step": 31000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.0162526041666666,
|
| 540 |
+
"grad_norm": 0.16703246533870697,
|
| 541 |
+
"learning_rate": 3.143671641844831e-05,
|
| 542 |
+
"loss": 2.6986,
|
| 543 |
+
"num_input_tokens_seen": 16697712121,
|
| 544 |
+
"step": 32000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.0162526041666666,
|
| 548 |
+
"eval_loss": 3.3022472858428955,
|
| 549 |
+
"eval_runtime": 156.1087,
|
| 550 |
+
"eval_samples_per_second": 117.867,
|
| 551 |
+
"eval_steps_per_second": 7.367,
|
| 552 |
+
"num_input_tokens_seen": 16697712121,
|
| 553 |
+
"step": 32000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.0051015625,
|
| 557 |
+
"grad_norm": 0.16916561126708984,
|
| 558 |
+
"learning_rate": 1.776541247281177e-05,
|
| 559 |
+
"loss": 2.6798,
|
| 560 |
+
"num_input_tokens_seen": 17219624329,
|
| 561 |
+
"step": 33000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.0051015625,
|
| 565 |
+
"eval_loss": 3.301964521408081,
|
| 566 |
+
"eval_runtime": 154.9317,
|
| 567 |
+
"eval_samples_per_second": 118.762,
|
| 568 |
+
"eval_steps_per_second": 7.423,
|
| 569 |
+
"num_input_tokens_seen": 17219624329,
|
| 570 |
+
"step": 33000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 5.013414930555555,
|
| 574 |
+
"grad_norm": 0.16186361014842987,
|
| 575 |
+
"learning_rate": 7.921936177411049e-06,
|
| 576 |
+
"loss": 2.6798,
|
| 577 |
+
"num_input_tokens_seen": 17741407609,
|
| 578 |
+
"step": 34000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 5.013414930555555,
|
| 582 |
+
"eval_loss": 3.300182580947876,
|
| 583 |
+
"eval_runtime": 155.5972,
|
| 584 |
+
"eval_samples_per_second": 118.254,
|
| 585 |
+
"eval_steps_per_second": 7.391,
|
| 586 |
+
"num_input_tokens_seen": 17741407609,
|
| 587 |
+
"step": 34000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 7.002003472222222,
|
| 591 |
+
"grad_norm": 0.1644630879163742,
|
| 592 |
+
"learning_rate": 1.984421974927375e-06,
|
| 593 |
+
"loss": 2.7195,
|
| 594 |
+
"num_input_tokens_seen": 18263254841,
|
| 595 |
+
"step": 35000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 7.002003472222222,
|
| 599 |
+
"eval_loss": 3.3019583225250244,
|
| 600 |
+
"eval_runtime": 155.6463,
|
| 601 |
+
"eval_samples_per_second": 118.217,
|
| 602 |
+
"eval_steps_per_second": 7.389,
|
| 603 |
+
"num_input_tokens_seen": 18263254841,
|
| 604 |
+
"step": 35000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.010214409722222,
|
| 608 |
+
"grad_norm": 0.1579432338476181,
|
| 609 |
+
"learning_rate": 0.0,
|
| 610 |
+
"loss": 2.683,
|
| 611 |
+
"num_input_tokens_seen": 18785262825,
|
| 612 |
+
"step": 36000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 8.010214409722222,
|
| 616 |
+
"eval_loss": 3.3019728660583496,
|
| 617 |
+
"eval_runtime": 155.7512,
|
| 618 |
+
"eval_samples_per_second": 118.137,
|
| 619 |
+
"eval_steps_per_second": 7.384,
|
| 620 |
+
"num_input_tokens_seen": 18785262825,
|
| 621 |
+
"step": 36000
|
| 622 |
+
}
|
| 623 |
+
],
|
| 624 |
+
"logging_steps": 1000,
|
| 625 |
+
"max_steps": 36000,
|
| 626 |
+
"num_input_tokens_seen": 18785262825,
|
| 627 |
+
"num_train_epochs": 9223372036854775807,
|
| 628 |
+
"save_steps": 1000,
|
| 629 |
+
"total_flos": 1.2950229157653494e+19,
|
| 630 |
+
"train_batch_size": 16,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a90dde8f1004134030a78307065f725a6ec4531e89718bce2e8d5dac7247db6
|
| 3 |
+
size 4984
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|