Add files using upload-large-folder tool
Browse files- checkpoint-100/vocab.json +0 -0
- checkpoint-1000/config.json +27 -0
- checkpoint-1400/config.json +27 -0
- checkpoint-1400/generation_config.json +9 -0
- checkpoint-1400/merges.txt +0 -0
- checkpoint-1400/special_tokens_map.json +30 -0
- checkpoint-1400/vocab.json +0 -0
- checkpoint-1500/generation_config.json +9 -0
- checkpoint-1500/special_tokens_map.json +30 -0
- checkpoint-1500/vocab.json +0 -0
- checkpoint-1600/tokenizer.json +0 -0
- checkpoint-1800/config.json +27 -0
- checkpoint-1800/latest +1 -0
- checkpoint-1800/merges.txt +0 -0
- checkpoint-1800/special_tokens_map.json +30 -0
- checkpoint-1800/trainer_state.json +1318 -0
- checkpoint-1900/special_tokens_map.json +30 -0
- checkpoint-1900/tokenizer.json +0 -0
- checkpoint-2100/chat_template.jinja +9 -0
- checkpoint-2100/config.json +27 -0
- checkpoint-2100/latest +1 -0
- checkpoint-2100/tokenizer_config.json +191 -0
- checkpoint-2100/trainer_state.json +1536 -0
- checkpoint-2200/chat_template.jinja +9 -0
- checkpoint-2200/config.json +27 -0
- checkpoint-2200/generation_config.json +9 -0
- checkpoint-2200/latest +1 -0
- checkpoint-2200/merges.txt +0 -0
- checkpoint-2200/special_tokens_map.json +30 -0
- checkpoint-2200/tokenizer_config.json +191 -0
- checkpoint-2200/trainer_state.json +1606 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2900/config.json +27 -0
- checkpoint-2900/generation_config.json +9 -0
- checkpoint-2900/tokenizer_config.json +191 -0
- checkpoint-2900/trainer_state.json +2104 -0
- checkpoint-2900/vocab.json +0 -0
- checkpoint-3000/vocab.json +0 -0
- checkpoint-3100/generation_config.json +9 -0
- checkpoint-3100/tokenizer.json +0 -0
- checkpoint-3200/generation_config.json +9 -0
- checkpoint-3300/generation_config.json +9 -0
- checkpoint-3332/tokenizer.json +0 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/vocab.json +0 -0
- checkpoint-600/generation_config.json +9 -0
- checkpoint-600/vocab.json +0 -0
- checkpoint-700/tokenizer.json +0 -0
- checkpoint-800/merges.txt +0 -0
- config.json +27 -0
checkpoint-100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-1400/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-1400/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-1400/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1400/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1600/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-1800/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step1800
|
checkpoint-1800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,1318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5402160864345739,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003001200480192077,
|
| 14 |
+
"grad_norm": 16.322778038786794,
|
| 15 |
+
"learning_rate": 2.694610778443114e-07,
|
| 16 |
+
"loss": 2.4961,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.006002400960384154,
|
| 21 |
+
"grad_norm": 21.26487128326307,
|
| 22 |
+
"learning_rate": 5.688622754491019e-07,
|
| 23 |
+
"loss": 2.4545,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00900360144057623,
|
| 28 |
+
"grad_norm": 20.493921349321404,
|
| 29 |
+
"learning_rate": 8.682634730538923e-07,
|
| 30 |
+
"loss": 2.4459,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.012004801920768308,
|
| 35 |
+
"grad_norm": 16.939655978226025,
|
| 36 |
+
"learning_rate": 1.1676646706586827e-06,
|
| 37 |
+
"loss": 2.4742,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.015006002400960384,
|
| 42 |
+
"grad_norm": 23.865531522300767,
|
| 43 |
+
"learning_rate": 1.4670658682634732e-06,
|
| 44 |
+
"loss": 2.0074,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01800720288115246,
|
| 49 |
+
"grad_norm": 16.606288718277256,
|
| 50 |
+
"learning_rate": 1.7664670658682636e-06,
|
| 51 |
+
"loss": 1.7784,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02100840336134454,
|
| 56 |
+
"grad_norm": 14.41517087399792,
|
| 57 |
+
"learning_rate": 2.065868263473054e-06,
|
| 58 |
+
"loss": 2.1435,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.024009603841536616,
|
| 63 |
+
"grad_norm": 9.610371534852842,
|
| 64 |
+
"learning_rate": 2.3652694610778446e-06,
|
| 65 |
+
"loss": 1.8848,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02701080432172869,
|
| 70 |
+
"grad_norm": 11.723596844563824,
|
| 71 |
+
"learning_rate": 2.664670658682635e-06,
|
| 72 |
+
"loss": 2.2553,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.030012004801920768,
|
| 77 |
+
"grad_norm": 28.025837302158916,
|
| 78 |
+
"learning_rate": 2.9640718562874255e-06,
|
| 79 |
+
"loss": 1.9136,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.033013205282112844,
|
| 84 |
+
"grad_norm": 9.44674022586452,
|
| 85 |
+
"learning_rate": 3.263473053892216e-06,
|
| 86 |
+
"loss": 2.1588,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03601440576230492,
|
| 91 |
+
"grad_norm": 12.826206690198743,
|
| 92 |
+
"learning_rate": 3.562874251497006e-06,
|
| 93 |
+
"loss": 1.9439,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.039015606242496996,
|
| 98 |
+
"grad_norm": 13.332854551269488,
|
| 99 |
+
"learning_rate": 3.862275449101797e-06,
|
| 100 |
+
"loss": 1.9872,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.04201680672268908,
|
| 105 |
+
"grad_norm": 13.687005134844258,
|
| 106 |
+
"learning_rate": 4.161676646706587e-06,
|
| 107 |
+
"loss": 2.018,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.045018007202881155,
|
| 112 |
+
"grad_norm": 11.10704695361387,
|
| 113 |
+
"learning_rate": 4.461077844311378e-06,
|
| 114 |
+
"loss": 1.8614,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.04801920768307323,
|
| 119 |
+
"grad_norm": 18.355044203461766,
|
| 120 |
+
"learning_rate": 4.760479041916168e-06,
|
| 121 |
+
"loss": 1.961,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05102040816326531,
|
| 126 |
+
"grad_norm": 15.09389345242339,
|
| 127 |
+
"learning_rate": 5.059880239520959e-06,
|
| 128 |
+
"loss": 2.21,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05402160864345738,
|
| 133 |
+
"grad_norm": 10.156004340051048,
|
| 134 |
+
"learning_rate": 5.359281437125749e-06,
|
| 135 |
+
"loss": 2.1261,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05702280912364946,
|
| 140 |
+
"grad_norm": 15.345968230792714,
|
| 141 |
+
"learning_rate": 5.658682634730539e-06,
|
| 142 |
+
"loss": 2.0072,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.060024009603841535,
|
| 147 |
+
"grad_norm": 11.153556976885293,
|
| 148 |
+
"learning_rate": 5.95808383233533e-06,
|
| 149 |
+
"loss": 1.9935,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.06302521008403361,
|
| 154 |
+
"grad_norm": 9.491849063073436,
|
| 155 |
+
"learning_rate": 6.25748502994012e-06,
|
| 156 |
+
"loss": 1.6912,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.06602641056422569,
|
| 161 |
+
"grad_norm": 9.775572755148744,
|
| 162 |
+
"learning_rate": 6.556886227544911e-06,
|
| 163 |
+
"loss": 2.2844,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06902761104441776,
|
| 168 |
+
"grad_norm": 10.444304091533951,
|
| 169 |
+
"learning_rate": 6.8562874251497016e-06,
|
| 170 |
+
"loss": 1.9957,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.07202881152460984,
|
| 175 |
+
"grad_norm": 12.315712653283379,
|
| 176 |
+
"learning_rate": 7.155688622754492e-06,
|
| 177 |
+
"loss": 1.718,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07503001200480192,
|
| 182 |
+
"grad_norm": 15.4266884794421,
|
| 183 |
+
"learning_rate": 7.4550898203592825e-06,
|
| 184 |
+
"loss": 1.8986,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07803121248499399,
|
| 189 |
+
"grad_norm": 15.350622303641131,
|
| 190 |
+
"learning_rate": 7.754491017964072e-06,
|
| 191 |
+
"loss": 2.1906,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.08103241296518607,
|
| 196 |
+
"grad_norm": 10.100826281853637,
|
| 197 |
+
"learning_rate": 8.053892215568863e-06,
|
| 198 |
+
"loss": 2.062,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08403361344537816,
|
| 203 |
+
"grad_norm": 9.985084559589948,
|
| 204 |
+
"learning_rate": 8.353293413173653e-06,
|
| 205 |
+
"loss": 2.0219,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08703481392557023,
|
| 210 |
+
"grad_norm": 25.52843769465498,
|
| 211 |
+
"learning_rate": 8.652694610778444e-06,
|
| 212 |
+
"loss": 1.774,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09003601440576231,
|
| 217 |
+
"grad_norm": 7.010526730435224,
|
| 218 |
+
"learning_rate": 8.952095808383234e-06,
|
| 219 |
+
"loss": 1.7647,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.09303721488595439,
|
| 224 |
+
"grad_norm": 10.925177037546252,
|
| 225 |
+
"learning_rate": 9.251497005988024e-06,
|
| 226 |
+
"loss": 1.853,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.09603841536614646,
|
| 231 |
+
"grad_norm": 13.12192108271367,
|
| 232 |
+
"learning_rate": 9.550898203592815e-06,
|
| 233 |
+
"loss": 2.023,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09903961584633854,
|
| 238 |
+
"grad_norm": 19.146417141785633,
|
| 239 |
+
"learning_rate": 9.850299401197606e-06,
|
| 240 |
+
"loss": 1.8804,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.10204081632653061,
|
| 245 |
+
"grad_norm": 17.095401175842863,
|
| 246 |
+
"learning_rate": 9.99993136976086e-06,
|
| 247 |
+
"loss": 2.0625,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.10504201680672269,
|
| 252 |
+
"grad_norm": 14.915026178785793,
|
| 253 |
+
"learning_rate": 9.99938233915195e-06,
|
| 254 |
+
"loss": 1.7554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.10804321728691477,
|
| 259 |
+
"grad_norm": 12.3557938764668,
|
| 260 |
+
"learning_rate": 9.99828433822188e-06,
|
| 261 |
+
"loss": 1.8197,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.11104441776710684,
|
| 266 |
+
"grad_norm": 16.732139399887032,
|
| 267 |
+
"learning_rate": 9.996637487539526e-06,
|
| 268 |
+
"loss": 1.9554,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.11404561824729892,
|
| 273 |
+
"grad_norm": 9.472954878862216,
|
| 274 |
+
"learning_rate": 9.99444196794166e-06,
|
| 275 |
+
"loss": 1.8419,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.117046818727491,
|
| 280 |
+
"grad_norm": 14.45943322716144,
|
| 281 |
+
"learning_rate": 9.99169802051308e-06,
|
| 282 |
+
"loss": 1.9554,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.12004801920768307,
|
| 287 |
+
"grad_norm": 11.816006243448049,
|
| 288 |
+
"learning_rate": 9.988405946560151e-06,
|
| 289 |
+
"loss": 1.6209,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12304921968787515,
|
| 294 |
+
"grad_norm": 19.870456146468612,
|
| 295 |
+
"learning_rate": 9.984566107577707e-06,
|
| 296 |
+
"loss": 2.1652,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.12605042016806722,
|
| 301 |
+
"grad_norm": 15.008106738503946,
|
| 302 |
+
"learning_rate": 9.980178925209363e-06,
|
| 303 |
+
"loss": 1.6964,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1290516206482593,
|
| 308 |
+
"grad_norm": 17.195341077337165,
|
| 309 |
+
"learning_rate": 9.975244881201209e-06,
|
| 310 |
+
"loss": 1.861,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.13205282112845138,
|
| 315 |
+
"grad_norm": 12.45396867483932,
|
| 316 |
+
"learning_rate": 9.969764517348924e-06,
|
| 317 |
+
"loss": 1.7937,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.13505402160864347,
|
| 322 |
+
"grad_norm": 9.707765043650019,
|
| 323 |
+
"learning_rate": 9.963738435438267e-06,
|
| 324 |
+
"loss": 1.956,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.13805522208883553,
|
| 329 |
+
"grad_norm": 12.149984169068404,
|
| 330 |
+
"learning_rate": 9.957167297179004e-06,
|
| 331 |
+
"loss": 1.9112,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.14105642256902762,
|
| 336 |
+
"grad_norm": 11.64329798977207,
|
| 337 |
+
"learning_rate": 9.950051824132247e-06,
|
| 338 |
+
"loss": 2.1092,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.14405762304921968,
|
| 343 |
+
"grad_norm": 13.559828016858319,
|
| 344 |
+
"learning_rate": 9.942392797631222e-06,
|
| 345 |
+
"loss": 2.0729,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14705882352941177,
|
| 350 |
+
"grad_norm": 15.255784576157163,
|
| 351 |
+
"learning_rate": 9.934191058695467e-06,
|
| 352 |
+
"loss": 1.9601,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.15006002400960383,
|
| 357 |
+
"grad_norm": 15.12208631421886,
|
| 358 |
+
"learning_rate": 9.925447507938493e-06,
|
| 359 |
+
"loss": 1.8079,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.15006002400960383,
|
| 364 |
+
"eval_loss": 1.8881598711013794,
|
| 365 |
+
"eval_runtime": 71.4162,
|
| 366 |
+
"eval_samples_per_second": 20.738,
|
| 367 |
+
"eval_steps_per_second": 10.376,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.15306122448979592,
|
| 372 |
+
"grad_norm": 9.812255338971053,
|
| 373 |
+
"learning_rate": 9.916163105468872e-06,
|
| 374 |
+
"loss": 1.9261,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.15606242496998798,
|
| 379 |
+
"grad_norm": 16.56967240161569,
|
| 380 |
+
"learning_rate": 9.90633887078483e-06,
|
| 381 |
+
"loss": 2.1224,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.15906362545018007,
|
| 386 |
+
"grad_norm": 10.921999649807898,
|
| 387 |
+
"learning_rate": 9.895975882662283e-06,
|
| 388 |
+
"loss": 1.7545,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.16206482593037214,
|
| 393 |
+
"grad_norm": 11.686083276616063,
|
| 394 |
+
"learning_rate": 9.885075279036385e-06,
|
| 395 |
+
"loss": 2.0052,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.16506602641056423,
|
| 400 |
+
"grad_norm": 13.670316963331478,
|
| 401 |
+
"learning_rate": 9.873638256876577e-06,
|
| 402 |
+
"loss": 1.8232,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.16806722689075632,
|
| 407 |
+
"grad_norm": 10.550976781841975,
|
| 408 |
+
"learning_rate": 9.861666072055144e-06,
|
| 409 |
+
"loss": 2.0087,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.17106842737094838,
|
| 414 |
+
"grad_norm": 7.518022216683535,
|
| 415 |
+
"learning_rate": 9.849160039209317e-06,
|
| 416 |
+
"loss": 2.0186,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.17406962785114047,
|
| 421 |
+
"grad_norm": 18.610725609857187,
|
| 422 |
+
"learning_rate": 9.83612153159691e-06,
|
| 423 |
+
"loss": 1.9651,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.17707082833133253,
|
| 428 |
+
"grad_norm": 14.468204525410128,
|
| 429 |
+
"learning_rate": 9.822551980945526e-06,
|
| 430 |
+
"loss": 1.8678,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.18007202881152462,
|
| 435 |
+
"grad_norm": 10.68638583134911,
|
| 436 |
+
"learning_rate": 9.808452877295356e-06,
|
| 437 |
+
"loss": 2.1099,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.18307322929171668,
|
| 442 |
+
"grad_norm": 6.8000928033318555,
|
| 443 |
+
"learning_rate": 9.79382576883554e-06,
|
| 444 |
+
"loss": 2.0071,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.18607442977190877,
|
| 449 |
+
"grad_norm": 9.517671427003565,
|
| 450 |
+
"learning_rate": 9.778672261734172e-06,
|
| 451 |
+
"loss": 2.2586,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.18907563025210083,
|
| 456 |
+
"grad_norm": 17.30722139026249,
|
| 457 |
+
"learning_rate": 9.762994019961944e-06,
|
| 458 |
+
"loss": 1.9017,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.19207683073229292,
|
| 463 |
+
"grad_norm": 7.832218568217347,
|
| 464 |
+
"learning_rate": 9.746792765109412e-06,
|
| 465 |
+
"loss": 2.0726,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.195078031212485,
|
| 470 |
+
"grad_norm": 15.595751845972346,
|
| 471 |
+
"learning_rate": 9.730070276197955e-06,
|
| 472 |
+
"loss": 2.1412,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.19807923169267708,
|
| 477 |
+
"grad_norm": 14.534725999964142,
|
| 478 |
+
"learning_rate": 9.712828389484432e-06,
|
| 479 |
+
"loss": 2.0257,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.20108043217286914,
|
| 484 |
+
"grad_norm": 9.963604466793788,
|
| 485 |
+
"learning_rate": 9.695068998259547e-06,
|
| 486 |
+
"loss": 1.9898,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.20408163265306123,
|
| 491 |
+
"grad_norm": 12.040002240054593,
|
| 492 |
+
"learning_rate": 9.676794052639937e-06,
|
| 493 |
+
"loss": 2.2448,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2070828331332533,
|
| 498 |
+
"grad_norm": 15.184552955496128,
|
| 499 |
+
"learning_rate": 9.658005559354053e-06,
|
| 500 |
+
"loss": 1.9303,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.21008403361344538,
|
| 505 |
+
"grad_norm": 10.529109691209351,
|
| 506 |
+
"learning_rate": 9.638705581521798e-06,
|
| 507 |
+
"loss": 1.9958,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.21308523409363744,
|
| 512 |
+
"grad_norm": 11.644168043518746,
|
| 513 |
+
"learning_rate": 9.618896238427973e-06,
|
| 514 |
+
"loss": 1.8387,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.21608643457382953,
|
| 519 |
+
"grad_norm": 10.27332830146538,
|
| 520 |
+
"learning_rate": 9.598579705289579e-06,
|
| 521 |
+
"loss": 1.9449,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2190876350540216,
|
| 526 |
+
"grad_norm": 5.679908324076684,
|
| 527 |
+
"learning_rate": 9.577758213016948e-06,
|
| 528 |
+
"loss": 2.0876,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.22208883553421369,
|
| 533 |
+
"grad_norm": 12.59216857148061,
|
| 534 |
+
"learning_rate": 9.55643404796878e-06,
|
| 535 |
+
"loss": 1.6231,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.22509003601440578,
|
| 540 |
+
"grad_norm": 11.87232412833194,
|
| 541 |
+
"learning_rate": 9.534609551701078e-06,
|
| 542 |
+
"loss": 1.7406,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.22809123649459784,
|
| 547 |
+
"grad_norm": 11.39859069066619,
|
| 548 |
+
"learning_rate": 9.512287120710032e-06,
|
| 549 |
+
"loss": 2.1341,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.23109243697478993,
|
| 554 |
+
"grad_norm": 9.182462389068496,
|
| 555 |
+
"learning_rate": 9.489469206168863e-06,
|
| 556 |
+
"loss": 1.8263,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.234093637454982,
|
| 561 |
+
"grad_norm": 7.77593574851048,
|
| 562 |
+
"learning_rate": 9.466158313658665e-06,
|
| 563 |
+
"loss": 2.0274,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.23709483793517408,
|
| 568 |
+
"grad_norm": 9.473304898118002,
|
| 569 |
+
"learning_rate": 9.442357002893275e-06,
|
| 570 |
+
"loss": 1.7858,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.24009603841536614,
|
| 575 |
+
"grad_norm": 12.918279823767726,
|
| 576 |
+
"learning_rate": 9.418067887438194e-06,
|
| 577 |
+
"loss": 1.9741,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.24309723889555823,
|
| 582 |
+
"grad_norm": 16.087139659433475,
|
| 583 |
+
"learning_rate": 9.393293634423604e-06,
|
| 584 |
+
"loss": 2.0156,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2460984393757503,
|
| 589 |
+
"grad_norm": 12.503098107833772,
|
| 590 |
+
"learning_rate": 9.368036964251488e-06,
|
| 591 |
+
"loss": 1.8051,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.24909963985594238,
|
| 596 |
+
"grad_norm": 17.921159341402873,
|
| 597 |
+
"learning_rate": 9.342300650296911e-06,
|
| 598 |
+
"loss": 2.0905,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.25210084033613445,
|
| 603 |
+
"grad_norm": 8.181948558613119,
|
| 604 |
+
"learning_rate": 9.316087518603491e-06,
|
| 605 |
+
"loss": 2.1614,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.25510204081632654,
|
| 610 |
+
"grad_norm": 12.386120651762177,
|
| 611 |
+
"learning_rate": 9.289400447573068e-06,
|
| 612 |
+
"loss": 1.9288,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.2581032412965186,
|
| 617 |
+
"grad_norm": 12.82368671615243,
|
| 618 |
+
"learning_rate": 9.262242367649637e-06,
|
| 619 |
+
"loss": 1.8841,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.26110444177671066,
|
| 624 |
+
"grad_norm": 11.682775075383281,
|
| 625 |
+
"learning_rate": 9.23461626099756e-06,
|
| 626 |
+
"loss": 1.8096,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.26410564225690275,
|
| 631 |
+
"grad_norm": 10.977666012081006,
|
| 632 |
+
"learning_rate": 9.20652516117411e-06,
|
| 633 |
+
"loss": 2.0035,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.26710684273709484,
|
| 638 |
+
"grad_norm": 10.140829194373916,
|
| 639 |
+
"learning_rate": 9.177972152796352e-06,
|
| 640 |
+
"loss": 1.8845,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.27010804321728693,
|
| 645 |
+
"grad_norm": 11.31872075294124,
|
| 646 |
+
"learning_rate": 9.148960371202442e-06,
|
| 647 |
+
"loss": 2.1503,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.27310924369747897,
|
| 652 |
+
"grad_norm": 15.07747778104917,
|
| 653 |
+
"learning_rate": 9.119493002107325e-06,
|
| 654 |
+
"loss": 2.1282,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.27611044417767105,
|
| 659 |
+
"grad_norm": 14.623330843128887,
|
| 660 |
+
"learning_rate": 9.089573281252938e-06,
|
| 661 |
+
"loss": 1.836,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.27911164465786314,
|
| 666 |
+
"grad_norm": 9.349353118072754,
|
| 667 |
+
"learning_rate": 9.059204494052884e-06,
|
| 668 |
+
"loss": 2.0206,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.28211284513805523,
|
| 673 |
+
"grad_norm": 13.132253499401044,
|
| 674 |
+
"learning_rate": 9.028389975231687e-06,
|
| 675 |
+
"loss": 2.0025,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2851140456182473,
|
| 680 |
+
"grad_norm": 8.77966207647504,
|
| 681 |
+
"learning_rate": 8.997133108458594e-06,
|
| 682 |
+
"loss": 2.0201,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.28811524609843936,
|
| 687 |
+
"grad_norm": 7.676366705721278,
|
| 688 |
+
"learning_rate": 8.965437325976036e-06,
|
| 689 |
+
"loss": 1.8401,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.29111644657863145,
|
| 694 |
+
"grad_norm": 17.688333111422782,
|
| 695 |
+
"learning_rate": 8.93330610822274e-06,
|
| 696 |
+
"loss": 1.7173,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.29411764705882354,
|
| 701 |
+
"grad_norm": 10.818948813957974,
|
| 702 |
+
"learning_rate": 8.900742983451538e-06,
|
| 703 |
+
"loss": 2.2006,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.29711884753901563,
|
| 708 |
+
"grad_norm": 10.149928390127263,
|
| 709 |
+
"learning_rate": 8.867751527341962e-06,
|
| 710 |
+
"loss": 2.0095,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.30012004801920766,
|
| 715 |
+
"grad_norm": 8.46959243433518,
|
| 716 |
+
"learning_rate": 8.834335362607578e-06,
|
| 717 |
+
"loss": 1.8346,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.30012004801920766,
|
| 722 |
+
"eval_loss": 1.8436174392700195,
|
| 723 |
+
"eval_runtime": 70.088,
|
| 724 |
+
"eval_samples_per_second": 21.131,
|
| 725 |
+
"eval_steps_per_second": 10.572,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.30312124849939975,
|
| 730 |
+
"grad_norm": 16.868801651903272,
|
| 731 |
+
"learning_rate": 8.80049815859821e-06,
|
| 732 |
+
"loss": 1.9479,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.30612244897959184,
|
| 737 |
+
"grad_norm": 10.50023341524374,
|
| 738 |
+
"learning_rate": 8.766243630897002e-06,
|
| 739 |
+
"loss": 2.1128,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.30912364945978393,
|
| 744 |
+
"grad_norm": 8.928156526275373,
|
| 745 |
+
"learning_rate": 8.731575540912422e-06,
|
| 746 |
+
"loss": 1.9959,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.31212484993997597,
|
| 751 |
+
"grad_norm": 11.834343384295739,
|
| 752 |
+
"learning_rate": 8.696497695465237e-06,
|
| 753 |
+
"loss": 1.8446,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.31512605042016806,
|
| 758 |
+
"grad_norm": 14.438889863331674,
|
| 759 |
+
"learning_rate": 8.66101394637048e-06,
|
| 760 |
+
"loss": 1.9538,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.31812725090036015,
|
| 765 |
+
"grad_norm": 7.0509264901284405,
|
| 766 |
+
"learning_rate": 8.625128190014513e-06,
|
| 767 |
+
"loss": 2.224,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.32112845138055224,
|
| 772 |
+
"grad_norm": 10.882784743186303,
|
| 773 |
+
"learning_rate": 8.588844366927156e-06,
|
| 774 |
+
"loss": 1.9669,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3241296518607443,
|
| 779 |
+
"grad_norm": 8.990237158612308,
|
| 780 |
+
"learning_rate": 8.552166461348991e-06,
|
| 781 |
+
"loss": 1.7175,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.32713085234093636,
|
| 786 |
+
"grad_norm": 14.10485370212862,
|
| 787 |
+
"learning_rate": 8.515098500793868e-06,
|
| 788 |
+
"loss": 1.9135,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.33013205282112845,
|
| 793 |
+
"grad_norm": 11.4270403766335,
|
| 794 |
+
"learning_rate": 8.477644555606647e-06,
|
| 795 |
+
"loss": 1.9181,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.33313325330132054,
|
| 800 |
+
"grad_norm": 10.98863933462178,
|
| 801 |
+
"learning_rate": 8.439808738516248e-06,
|
| 802 |
+
"loss": 2.0249,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.33613445378151263,
|
| 807 |
+
"grad_norm": 21.402837855150903,
|
| 808 |
+
"learning_rate": 8.401595204184035e-06,
|
| 809 |
+
"loss": 1.7287,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.33913565426170467,
|
| 814 |
+
"grad_norm": 13.977226200369794,
|
| 815 |
+
"learning_rate": 8.363008148747606e-06,
|
| 816 |
+
"loss": 1.7275,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.34213685474189676,
|
| 821 |
+
"grad_norm": 12.329315260812974,
|
| 822 |
+
"learning_rate": 8.324051809360037e-06,
|
| 823 |
+
"loss": 1.9854,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.34513805522208885,
|
| 828 |
+
"grad_norm": 6.8949526667461125,
|
| 829 |
+
"learning_rate": 8.284730463724585e-06,
|
| 830 |
+
"loss": 1.8173,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.34813925570228094,
|
| 835 |
+
"grad_norm": 15.132137249007318,
|
| 836 |
+
"learning_rate": 8.245048429624983e-06,
|
| 837 |
+
"loss": 2.0162,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.35114045618247297,
|
| 842 |
+
"grad_norm": 11.463625138426867,
|
| 843 |
+
"learning_rate": 8.205010064451314e-06,
|
| 844 |
+
"loss": 2.2115,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.35414165666266506,
|
| 849 |
+
"grad_norm": 12.725809570070531,
|
| 850 |
+
"learning_rate": 8.164619764721523e-06,
|
| 851 |
+
"loss": 2.204,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.35714285714285715,
|
| 856 |
+
"grad_norm": 12.730243560834372,
|
| 857 |
+
"learning_rate": 8.12388196559866e-06,
|
| 858 |
+
"loss": 1.897,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.36014405762304924,
|
| 863 |
+
"grad_norm": 7.029827177766862,
|
| 864 |
+
"learning_rate": 8.082801140403857e-06,
|
| 865 |
+
"loss": 1.7744,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.3631452581032413,
|
| 870 |
+
"grad_norm": 10.414460517503901,
|
| 871 |
+
"learning_rate": 8.041381800125129e-06,
|
| 872 |
+
"loss": 1.8452,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.36614645858343337,
|
| 877 |
+
"grad_norm": 13.745072092763401,
|
| 878 |
+
"learning_rate": 7.999628492922022e-06,
|
| 879 |
+
"loss": 2.0646,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.36914765906362546,
|
| 884 |
+
"grad_norm": 8.775551099349842,
|
| 885 |
+
"learning_rate": 7.957545803626208e-06,
|
| 886 |
+
"loss": 1.9013,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.37214885954381755,
|
| 891 |
+
"grad_norm": 12.599490709310933,
|
| 892 |
+
"learning_rate": 7.915138353238018e-06,
|
| 893 |
+
"loss": 2.0367,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.3751500600240096,
|
| 898 |
+
"grad_norm": 6.256535396667515,
|
| 899 |
+
"learning_rate": 7.872410798419033e-06,
|
| 900 |
+
"loss": 1.9974,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.37815126050420167,
|
| 905 |
+
"grad_norm": 9.33884703529061,
|
| 906 |
+
"learning_rate": 7.829367830980739e-06,
|
| 907 |
+
"loss": 1.9962,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.38115246098439376,
|
| 912 |
+
"grad_norm": 21.706114177368843,
|
| 913 |
+
"learning_rate": 7.786014177369336e-06,
|
| 914 |
+
"loss": 1.9969,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.38415366146458585,
|
| 919 |
+
"grad_norm": 12.19292284047377,
|
| 920 |
+
"learning_rate": 7.742354598146737e-06,
|
| 921 |
+
"loss": 2.0981,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3871548619447779,
|
| 926 |
+
"grad_norm": 9.306186302055167,
|
| 927 |
+
"learning_rate": 7.698393887467822e-06,
|
| 928 |
+
"loss": 1.9351,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.39015606242497,
|
| 933 |
+
"grad_norm": 7.075234259359012,
|
| 934 |
+
"learning_rate": 7.654136872553994e-06,
|
| 935 |
+
"loss": 2.0849,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.39315726290516206,
|
| 940 |
+
"grad_norm": 13.098710223009212,
|
| 941 |
+
"learning_rate": 7.609588413163133e-06,
|
| 942 |
+
"loss": 2.1268,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.39615846338535415,
|
| 947 |
+
"grad_norm": 8.116612120897077,
|
| 948 |
+
"learning_rate": 7.564753401055938e-06,
|
| 949 |
+
"loss": 2.1511,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.39915966386554624,
|
| 954 |
+
"grad_norm": 11.134740327279541,
|
| 955 |
+
"learning_rate": 7.519636759458787e-06,
|
| 956 |
+
"loss": 1.8251,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4021608643457383,
|
| 961 |
+
"grad_norm": 7.351044801101755,
|
| 962 |
+
"learning_rate": 7.474243442523122e-06,
|
| 963 |
+
"loss": 1.9105,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.40516206482593037,
|
| 968 |
+
"grad_norm": 13.084121400843905,
|
| 969 |
+
"learning_rate": 7.428578434781446e-06,
|
| 970 |
+
"loss": 2.0436,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.40816326530612246,
|
| 975 |
+
"grad_norm": 9.072398206431368,
|
| 976 |
+
"learning_rate": 7.382646750599991e-06,
|
| 977 |
+
"loss": 1.9403,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.41116446578631455,
|
| 982 |
+
"grad_norm": 10.586715140991426,
|
| 983 |
+
"learning_rate": 7.33645343362809e-06,
|
| 984 |
+
"loss": 2.0718,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.4141656662665066,
|
| 989 |
+
"grad_norm": 11.515109253824,
|
| 990 |
+
"learning_rate": 7.290003556244359e-06,
|
| 991 |
+
"loss": 1.8263,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4171668667466987,
|
| 996 |
+
"grad_norm": 11.730876807196703,
|
| 997 |
+
"learning_rate": 7.2433022189997e-06,
|
| 998 |
+
"loss": 1.9503,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.42016806722689076,
|
| 1003 |
+
"grad_norm": 10.550292645454324,
|
| 1004 |
+
"learning_rate": 7.196354550057226e-06,
|
| 1005 |
+
"loss": 1.8239,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.42316926770708285,
|
| 1010 |
+
"grad_norm": 9.887874814498124,
|
| 1011 |
+
"learning_rate": 7.1491657046291526e-06,
|
| 1012 |
+
"loss": 1.9299,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4261704681872749,
|
| 1017 |
+
"grad_norm": 12.616008529269662,
|
| 1018 |
+
"learning_rate": 7.101740864410709e-06,
|
| 1019 |
+
"loss": 2.1525,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.429171668667467,
|
| 1024 |
+
"grad_norm": 8.812376323246953,
|
| 1025 |
+
"learning_rate": 7.05408523701116e-06,
|
| 1026 |
+
"loss": 1.8238,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.43217286914765907,
|
| 1031 |
+
"grad_norm": 8.745128290955817,
|
| 1032 |
+
"learning_rate": 7.006204055381957e-06,
|
| 1033 |
+
"loss": 1.6758,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.43517406962785116,
|
| 1038 |
+
"grad_norm": 6.318402234130335,
|
| 1039 |
+
"learning_rate": 6.958102577242128e-06,
|
| 1040 |
+
"loss": 1.9202,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.4381752701080432,
|
| 1045 |
+
"grad_norm": 7.927574856182854,
|
| 1046 |
+
"learning_rate": 6.909786084500939e-06,
|
| 1047 |
+
"loss": 2.0833,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4411764705882353,
|
| 1052 |
+
"grad_norm": 10.544936971680398,
|
| 1053 |
+
"learning_rate": 6.861259882677902e-06,
|
| 1054 |
+
"loss": 2.002,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.44417767106842737,
|
| 1059 |
+
"grad_norm": 11.619710218418861,
|
| 1060 |
+
"learning_rate": 6.8125293003201806e-06,
|
| 1061 |
+
"loss": 1.7993,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.44717887154861946,
|
| 1066 |
+
"grad_norm": 6.420503958767878,
|
| 1067 |
+
"learning_rate": 6.763599688417487e-06,
|
| 1068 |
+
"loss": 1.8841,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.45018007202881155,
|
| 1073 |
+
"grad_norm": 12.533300979520721,
|
| 1074 |
+
"learning_rate": 6.714476419814492e-06,
|
| 1075 |
+
"loss": 1.9325,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.45018007202881155,
|
| 1080 |
+
"eval_loss": 1.7854255437850952,
|
| 1081 |
+
"eval_runtime": 72.7355,
|
| 1082 |
+
"eval_samples_per_second": 20.361,
|
| 1083 |
+
"eval_steps_per_second": 10.188,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.4531812725090036,
|
| 1088 |
+
"grad_norm": 4.747847172239305,
|
| 1089 |
+
"learning_rate": 6.665164888620848e-06,
|
| 1090 |
+
"loss": 1.6663,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.4561824729891957,
|
| 1095 |
+
"grad_norm": 7.525229479358654,
|
| 1096 |
+
"learning_rate": 6.615670509618879e-06,
|
| 1097 |
+
"loss": 1.6184,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.45918367346938777,
|
| 1102 |
+
"grad_norm": 9.73553436099885,
|
| 1103 |
+
"learning_rate": 6.565998717668992e-06,
|
| 1104 |
+
"loss": 2.0157,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.46218487394957986,
|
| 1109 |
+
"grad_norm": 1.9365788113666345,
|
| 1110 |
+
"learning_rate": 6.516154967112891e-06,
|
| 1111 |
+
"loss": 1.5343,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.4651860744297719,
|
| 1116 |
+
"grad_norm": 13.65674435295188,
|
| 1117 |
+
"learning_rate": 6.466144731174645e-06,
|
| 1118 |
+
"loss": 1.8785,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.468187274909964,
|
| 1123 |
+
"grad_norm": 12.365721091880623,
|
| 1124 |
+
"learning_rate": 6.415973501359687e-06,
|
| 1125 |
+
"loss": 1.7204,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.47118847539015607,
|
| 1130 |
+
"grad_norm": 6.498996459559609,
|
| 1131 |
+
"learning_rate": 6.365646786851809e-06,
|
| 1132 |
+
"loss": 1.9123,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.47418967587034816,
|
| 1137 |
+
"grad_norm": 12.248966426285023,
|
| 1138 |
+
"learning_rate": 6.315170113908204e-06,
|
| 1139 |
+
"loss": 2.0724,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.4771908763505402,
|
| 1144 |
+
"grad_norm": 6.254751069477799,
|
| 1145 |
+
"learning_rate": 6.264549025252652e-06,
|
| 1146 |
+
"loss": 2.0417,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4801920768307323,
|
| 1151 |
+
"grad_norm": 11.586505827936087,
|
| 1152 |
+
"learning_rate": 6.213789079466873e-06,
|
| 1153 |
+
"loss": 1.9998,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4831932773109244,
|
| 1158 |
+
"grad_norm": 11.628169667737911,
|
| 1159 |
+
"learning_rate": 6.1628958503801635e-06,
|
| 1160 |
+
"loss": 1.9805,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.48619447779111646,
|
| 1165 |
+
"grad_norm": 10.266695075168396,
|
| 1166 |
+
"learning_rate": 6.111874926457344e-06,
|
| 1167 |
+
"loss": 1.9866,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.4891956782713085,
|
| 1172 |
+
"grad_norm": 7.864602445607685,
|
| 1173 |
+
"learning_rate": 6.0607319101850955e-06,
|
| 1174 |
+
"loss": 2.0325,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4921968787515006,
|
| 1179 |
+
"grad_norm": 7.852131699169073,
|
| 1180 |
+
"learning_rate": 6.009472417456779e-06,
|
| 1181 |
+
"loss": 2.136,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4951980792316927,
|
| 1186 |
+
"grad_norm": 9.171127473935298,
|
| 1187 |
+
"learning_rate": 5.958102076955753e-06,
|
| 1188 |
+
"loss": 1.8371,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.49819927971188477,
|
| 1193 |
+
"grad_norm": 13.155484650564988,
|
| 1194 |
+
"learning_rate": 5.906626529537311e-06,
|
| 1195 |
+
"loss": 2.1112,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.5012004801920769,
|
| 1200 |
+
"grad_norm": 14.407405269785295,
|
| 1201 |
+
"learning_rate": 5.855051427609265e-06,
|
| 1202 |
+
"loss": 2.1317,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.5042016806722689,
|
| 1207 |
+
"grad_norm": 7.944398594556855,
|
| 1208 |
+
"learning_rate": 5.803382434511274e-06,
|
| 1209 |
+
"loss": 1.9131,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.507202881152461,
|
| 1214 |
+
"grad_norm": 12.067931060345453,
|
| 1215 |
+
"learning_rate": 5.751625223892964e-06,
|
| 1216 |
+
"loss": 1.961,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.5102040816326531,
|
| 1221 |
+
"grad_norm": 11.305421590297874,
|
| 1222 |
+
"learning_rate": 5.699785479090917e-06,
|
| 1223 |
+
"loss": 1.8233,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.5132052821128451,
|
| 1228 |
+
"grad_norm": 10.568805120830348,
|
| 1229 |
+
"learning_rate": 5.647868892504597e-06,
|
| 1230 |
+
"loss": 1.8034,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.5162064825930373,
|
| 1235 |
+
"grad_norm": 8.901920906884708,
|
| 1236 |
+
"learning_rate": 5.595881164971284e-06,
|
| 1237 |
+
"loss": 2.1088,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.5192076830732293,
|
| 1242 |
+
"grad_norm": 10.818151872015115,
|
| 1243 |
+
"learning_rate": 5.543828005140076e-06,
|
| 1244 |
+
"loss": 1.9505,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.5222088835534213,
|
| 1249 |
+
"grad_norm": 19.0269528128246,
|
| 1250 |
+
"learning_rate": 5.491715128845037e-06,
|
| 1251 |
+
"loss": 2.1158,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.5252100840336135,
|
| 1256 |
+
"grad_norm": 6.368156672789348,
|
| 1257 |
+
"learning_rate": 5.439548258477549e-06,
|
| 1258 |
+
"loss": 1.526,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.5282112845138055,
|
| 1263 |
+
"grad_norm": 14.33226946197169,
|
| 1264 |
+
"learning_rate": 5.387333122357966e-06,
|
| 1265 |
+
"loss": 1.9441,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5312124849939976,
|
| 1270 |
+
"grad_norm": 10.893640588904004,
|
| 1271 |
+
"learning_rate": 5.3350754541065805e-06,
|
| 1272 |
+
"loss": 1.5771,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5342136854741897,
|
| 1277 |
+
"grad_norm": 11.613038829759443,
|
| 1278 |
+
"learning_rate": 5.282780992014043e-06,
|
| 1279 |
+
"loss": 1.8335,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.5372148859543817,
|
| 1284 |
+
"grad_norm": 6.446614047723568,
|
| 1285 |
+
"learning_rate": 5.230455478411243e-06,
|
| 1286 |
+
"loss": 1.9638,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5402160864345739,
|
| 1291 |
+
"grad_norm": 14.258595482993,
|
| 1292 |
+
"learning_rate": 5.1781046590387675e-06,
|
| 1293 |
+
"loss": 1.8887,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
}
|
| 1296 |
+
],
|
| 1297 |
+
"logging_steps": 10,
|
| 1298 |
+
"max_steps": 3332,
|
| 1299 |
+
"num_input_tokens_seen": 0,
|
| 1300 |
+
"num_train_epochs": 1,
|
| 1301 |
+
"save_steps": 100,
|
| 1302 |
+
"stateful_callbacks": {
|
| 1303 |
+
"TrainerControl": {
|
| 1304 |
+
"args": {
|
| 1305 |
+
"should_epoch_stop": false,
|
| 1306 |
+
"should_evaluate": false,
|
| 1307 |
+
"should_log": false,
|
| 1308 |
+
"should_save": true,
|
| 1309 |
+
"should_training_stop": false
|
| 1310 |
+
},
|
| 1311 |
+
"attributes": {}
|
| 1312 |
+
}
|
| 1313 |
+
},
|
| 1314 |
+
"total_flos": 2060122521600.0,
|
| 1315 |
+
"train_batch_size": 2,
|
| 1316 |
+
"trial_name": null,
|
| 1317 |
+
"trial_params": null
|
| 1318 |
+
}
|
checkpoint-1900/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-1900/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2100/chat_template.jinja
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
|
| 2 |
+
' + message['content'] + '
|
| 3 |
+
' }}{% elif message['role'] == 'user' %}{{ '<|user|>
|
| 4 |
+
' + message['content'] + '
|
| 5 |
+
' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
|
| 6 |
+
' + message['content'] + eos_token + '
|
| 7 |
+
' }}{% else %}{{ '<|assistant|>
|
| 8 |
+
' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
|
| 9 |
+
' }}{% endif %}{% endfor %}
|
checkpoint-2100/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-2100/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step2100
|
checkpoint-2100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 186 |
+
"pad_token": "<|pad|>",
|
| 187 |
+
"padding_side": "right",
|
| 188 |
+
"split_special_tokens": false,
|
| 189 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 190 |
+
"unk_token": "<|endoftext|>"
|
| 191 |
+
}
|
checkpoint-2100/trainer_state.json
ADDED
|
@@ -0,0 +1,1536 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6302521008403361,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003001200480192077,
|
| 14 |
+
"grad_norm": 16.322778038786794,
|
| 15 |
+
"learning_rate": 2.694610778443114e-07,
|
| 16 |
+
"loss": 2.4961,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.006002400960384154,
|
| 21 |
+
"grad_norm": 21.26487128326307,
|
| 22 |
+
"learning_rate": 5.688622754491019e-07,
|
| 23 |
+
"loss": 2.4545,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00900360144057623,
|
| 28 |
+
"grad_norm": 20.493921349321404,
|
| 29 |
+
"learning_rate": 8.682634730538923e-07,
|
| 30 |
+
"loss": 2.4459,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.012004801920768308,
|
| 35 |
+
"grad_norm": 16.939655978226025,
|
| 36 |
+
"learning_rate": 1.1676646706586827e-06,
|
| 37 |
+
"loss": 2.4742,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.015006002400960384,
|
| 42 |
+
"grad_norm": 23.865531522300767,
|
| 43 |
+
"learning_rate": 1.4670658682634732e-06,
|
| 44 |
+
"loss": 2.0074,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01800720288115246,
|
| 49 |
+
"grad_norm": 16.606288718277256,
|
| 50 |
+
"learning_rate": 1.7664670658682636e-06,
|
| 51 |
+
"loss": 1.7784,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02100840336134454,
|
| 56 |
+
"grad_norm": 14.41517087399792,
|
| 57 |
+
"learning_rate": 2.065868263473054e-06,
|
| 58 |
+
"loss": 2.1435,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.024009603841536616,
|
| 63 |
+
"grad_norm": 9.610371534852842,
|
| 64 |
+
"learning_rate": 2.3652694610778446e-06,
|
| 65 |
+
"loss": 1.8848,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02701080432172869,
|
| 70 |
+
"grad_norm": 11.723596844563824,
|
| 71 |
+
"learning_rate": 2.664670658682635e-06,
|
| 72 |
+
"loss": 2.2553,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.030012004801920768,
|
| 77 |
+
"grad_norm": 28.025837302158916,
|
| 78 |
+
"learning_rate": 2.9640718562874255e-06,
|
| 79 |
+
"loss": 1.9136,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.033013205282112844,
|
| 84 |
+
"grad_norm": 9.44674022586452,
|
| 85 |
+
"learning_rate": 3.263473053892216e-06,
|
| 86 |
+
"loss": 2.1588,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03601440576230492,
|
| 91 |
+
"grad_norm": 12.826206690198743,
|
| 92 |
+
"learning_rate": 3.562874251497006e-06,
|
| 93 |
+
"loss": 1.9439,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.039015606242496996,
|
| 98 |
+
"grad_norm": 13.332854551269488,
|
| 99 |
+
"learning_rate": 3.862275449101797e-06,
|
| 100 |
+
"loss": 1.9872,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.04201680672268908,
|
| 105 |
+
"grad_norm": 13.687005134844258,
|
| 106 |
+
"learning_rate": 4.161676646706587e-06,
|
| 107 |
+
"loss": 2.018,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.045018007202881155,
|
| 112 |
+
"grad_norm": 11.10704695361387,
|
| 113 |
+
"learning_rate": 4.461077844311378e-06,
|
| 114 |
+
"loss": 1.8614,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.04801920768307323,
|
| 119 |
+
"grad_norm": 18.355044203461766,
|
| 120 |
+
"learning_rate": 4.760479041916168e-06,
|
| 121 |
+
"loss": 1.961,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05102040816326531,
|
| 126 |
+
"grad_norm": 15.09389345242339,
|
| 127 |
+
"learning_rate": 5.059880239520959e-06,
|
| 128 |
+
"loss": 2.21,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05402160864345738,
|
| 133 |
+
"grad_norm": 10.156004340051048,
|
| 134 |
+
"learning_rate": 5.359281437125749e-06,
|
| 135 |
+
"loss": 2.1261,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05702280912364946,
|
| 140 |
+
"grad_norm": 15.345968230792714,
|
| 141 |
+
"learning_rate": 5.658682634730539e-06,
|
| 142 |
+
"loss": 2.0072,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.060024009603841535,
|
| 147 |
+
"grad_norm": 11.153556976885293,
|
| 148 |
+
"learning_rate": 5.95808383233533e-06,
|
| 149 |
+
"loss": 1.9935,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.06302521008403361,
|
| 154 |
+
"grad_norm": 9.491849063073436,
|
| 155 |
+
"learning_rate": 6.25748502994012e-06,
|
| 156 |
+
"loss": 1.6912,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.06602641056422569,
|
| 161 |
+
"grad_norm": 9.775572755148744,
|
| 162 |
+
"learning_rate": 6.556886227544911e-06,
|
| 163 |
+
"loss": 2.2844,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06902761104441776,
|
| 168 |
+
"grad_norm": 10.444304091533951,
|
| 169 |
+
"learning_rate": 6.8562874251497016e-06,
|
| 170 |
+
"loss": 1.9957,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.07202881152460984,
|
| 175 |
+
"grad_norm": 12.315712653283379,
|
| 176 |
+
"learning_rate": 7.155688622754492e-06,
|
| 177 |
+
"loss": 1.718,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07503001200480192,
|
| 182 |
+
"grad_norm": 15.4266884794421,
|
| 183 |
+
"learning_rate": 7.4550898203592825e-06,
|
| 184 |
+
"loss": 1.8986,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07803121248499399,
|
| 189 |
+
"grad_norm": 15.350622303641131,
|
| 190 |
+
"learning_rate": 7.754491017964072e-06,
|
| 191 |
+
"loss": 2.1906,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.08103241296518607,
|
| 196 |
+
"grad_norm": 10.100826281853637,
|
| 197 |
+
"learning_rate": 8.053892215568863e-06,
|
| 198 |
+
"loss": 2.062,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08403361344537816,
|
| 203 |
+
"grad_norm": 9.985084559589948,
|
| 204 |
+
"learning_rate": 8.353293413173653e-06,
|
| 205 |
+
"loss": 2.0219,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08703481392557023,
|
| 210 |
+
"grad_norm": 25.52843769465498,
|
| 211 |
+
"learning_rate": 8.652694610778444e-06,
|
| 212 |
+
"loss": 1.774,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09003601440576231,
|
| 217 |
+
"grad_norm": 7.010526730435224,
|
| 218 |
+
"learning_rate": 8.952095808383234e-06,
|
| 219 |
+
"loss": 1.7647,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.09303721488595439,
|
| 224 |
+
"grad_norm": 10.925177037546252,
|
| 225 |
+
"learning_rate": 9.251497005988024e-06,
|
| 226 |
+
"loss": 1.853,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.09603841536614646,
|
| 231 |
+
"grad_norm": 13.12192108271367,
|
| 232 |
+
"learning_rate": 9.550898203592815e-06,
|
| 233 |
+
"loss": 2.023,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09903961584633854,
|
| 238 |
+
"grad_norm": 19.146417141785633,
|
| 239 |
+
"learning_rate": 9.850299401197606e-06,
|
| 240 |
+
"loss": 1.8804,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.10204081632653061,
|
| 245 |
+
"grad_norm": 17.095401175842863,
|
| 246 |
+
"learning_rate": 9.99993136976086e-06,
|
| 247 |
+
"loss": 2.0625,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.10504201680672269,
|
| 252 |
+
"grad_norm": 14.915026178785793,
|
| 253 |
+
"learning_rate": 9.99938233915195e-06,
|
| 254 |
+
"loss": 1.7554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.10804321728691477,
|
| 259 |
+
"grad_norm": 12.3557938764668,
|
| 260 |
+
"learning_rate": 9.99828433822188e-06,
|
| 261 |
+
"loss": 1.8197,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.11104441776710684,
|
| 266 |
+
"grad_norm": 16.732139399887032,
|
| 267 |
+
"learning_rate": 9.996637487539526e-06,
|
| 268 |
+
"loss": 1.9554,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.11404561824729892,
|
| 273 |
+
"grad_norm": 9.472954878862216,
|
| 274 |
+
"learning_rate": 9.99444196794166e-06,
|
| 275 |
+
"loss": 1.8419,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.117046818727491,
|
| 280 |
+
"grad_norm": 14.45943322716144,
|
| 281 |
+
"learning_rate": 9.99169802051308e-06,
|
| 282 |
+
"loss": 1.9554,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.12004801920768307,
|
| 287 |
+
"grad_norm": 11.816006243448049,
|
| 288 |
+
"learning_rate": 9.988405946560151e-06,
|
| 289 |
+
"loss": 1.6209,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12304921968787515,
|
| 294 |
+
"grad_norm": 19.870456146468612,
|
| 295 |
+
"learning_rate": 9.984566107577707e-06,
|
| 296 |
+
"loss": 2.1652,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.12605042016806722,
|
| 301 |
+
"grad_norm": 15.008106738503946,
|
| 302 |
+
"learning_rate": 9.980178925209363e-06,
|
| 303 |
+
"loss": 1.6964,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1290516206482593,
|
| 308 |
+
"grad_norm": 17.195341077337165,
|
| 309 |
+
"learning_rate": 9.975244881201209e-06,
|
| 310 |
+
"loss": 1.861,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.13205282112845138,
|
| 315 |
+
"grad_norm": 12.45396867483932,
|
| 316 |
+
"learning_rate": 9.969764517348924e-06,
|
| 317 |
+
"loss": 1.7937,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.13505402160864347,
|
| 322 |
+
"grad_norm": 9.707765043650019,
|
| 323 |
+
"learning_rate": 9.963738435438267e-06,
|
| 324 |
+
"loss": 1.956,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.13805522208883553,
|
| 329 |
+
"grad_norm": 12.149984169068404,
|
| 330 |
+
"learning_rate": 9.957167297179004e-06,
|
| 331 |
+
"loss": 1.9112,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.14105642256902762,
|
| 336 |
+
"grad_norm": 11.64329798977207,
|
| 337 |
+
"learning_rate": 9.950051824132247e-06,
|
| 338 |
+
"loss": 2.1092,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.14405762304921968,
|
| 343 |
+
"grad_norm": 13.559828016858319,
|
| 344 |
+
"learning_rate": 9.942392797631222e-06,
|
| 345 |
+
"loss": 2.0729,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14705882352941177,
|
| 350 |
+
"grad_norm": 15.255784576157163,
|
| 351 |
+
"learning_rate": 9.934191058695467e-06,
|
| 352 |
+
"loss": 1.9601,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.15006002400960383,
|
| 357 |
+
"grad_norm": 15.12208631421886,
|
| 358 |
+
"learning_rate": 9.925447507938493e-06,
|
| 359 |
+
"loss": 1.8079,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.15006002400960383,
|
| 364 |
+
"eval_loss": 1.8881598711013794,
|
| 365 |
+
"eval_runtime": 71.4162,
|
| 366 |
+
"eval_samples_per_second": 20.738,
|
| 367 |
+
"eval_steps_per_second": 10.376,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.15306122448979592,
|
| 372 |
+
"grad_norm": 9.812255338971053,
|
| 373 |
+
"learning_rate": 9.916163105468872e-06,
|
| 374 |
+
"loss": 1.9261,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.15606242496998798,
|
| 379 |
+
"grad_norm": 16.56967240161569,
|
| 380 |
+
"learning_rate": 9.90633887078483e-06,
|
| 381 |
+
"loss": 2.1224,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.15906362545018007,
|
| 386 |
+
"grad_norm": 10.921999649807898,
|
| 387 |
+
"learning_rate": 9.895975882662283e-06,
|
| 388 |
+
"loss": 1.7545,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.16206482593037214,
|
| 393 |
+
"grad_norm": 11.686083276616063,
|
| 394 |
+
"learning_rate": 9.885075279036385e-06,
|
| 395 |
+
"loss": 2.0052,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.16506602641056423,
|
| 400 |
+
"grad_norm": 13.670316963331478,
|
| 401 |
+
"learning_rate": 9.873638256876577e-06,
|
| 402 |
+
"loss": 1.8232,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.16806722689075632,
|
| 407 |
+
"grad_norm": 10.550976781841975,
|
| 408 |
+
"learning_rate": 9.861666072055144e-06,
|
| 409 |
+
"loss": 2.0087,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.17106842737094838,
|
| 414 |
+
"grad_norm": 7.518022216683535,
|
| 415 |
+
"learning_rate": 9.849160039209317e-06,
|
| 416 |
+
"loss": 2.0186,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.17406962785114047,
|
| 421 |
+
"grad_norm": 18.610725609857187,
|
| 422 |
+
"learning_rate": 9.83612153159691e-06,
|
| 423 |
+
"loss": 1.9651,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.17707082833133253,
|
| 428 |
+
"grad_norm": 14.468204525410128,
|
| 429 |
+
"learning_rate": 9.822551980945526e-06,
|
| 430 |
+
"loss": 1.8678,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.18007202881152462,
|
| 435 |
+
"grad_norm": 10.68638583134911,
|
| 436 |
+
"learning_rate": 9.808452877295356e-06,
|
| 437 |
+
"loss": 2.1099,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.18307322929171668,
|
| 442 |
+
"grad_norm": 6.8000928033318555,
|
| 443 |
+
"learning_rate": 9.79382576883554e-06,
|
| 444 |
+
"loss": 2.0071,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.18607442977190877,
|
| 449 |
+
"grad_norm": 9.517671427003565,
|
| 450 |
+
"learning_rate": 9.778672261734172e-06,
|
| 451 |
+
"loss": 2.2586,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.18907563025210083,
|
| 456 |
+
"grad_norm": 17.30722139026249,
|
| 457 |
+
"learning_rate": 9.762994019961944e-06,
|
| 458 |
+
"loss": 1.9017,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.19207683073229292,
|
| 463 |
+
"grad_norm": 7.832218568217347,
|
| 464 |
+
"learning_rate": 9.746792765109412e-06,
|
| 465 |
+
"loss": 2.0726,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.195078031212485,
|
| 470 |
+
"grad_norm": 15.595751845972346,
|
| 471 |
+
"learning_rate": 9.730070276197955e-06,
|
| 472 |
+
"loss": 2.1412,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.19807923169267708,
|
| 477 |
+
"grad_norm": 14.534725999964142,
|
| 478 |
+
"learning_rate": 9.712828389484432e-06,
|
| 479 |
+
"loss": 2.0257,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.20108043217286914,
|
| 484 |
+
"grad_norm": 9.963604466793788,
|
| 485 |
+
"learning_rate": 9.695068998259547e-06,
|
| 486 |
+
"loss": 1.9898,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.20408163265306123,
|
| 491 |
+
"grad_norm": 12.040002240054593,
|
| 492 |
+
"learning_rate": 9.676794052639937e-06,
|
| 493 |
+
"loss": 2.2448,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2070828331332533,
|
| 498 |
+
"grad_norm": 15.184552955496128,
|
| 499 |
+
"learning_rate": 9.658005559354053e-06,
|
| 500 |
+
"loss": 1.9303,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.21008403361344538,
|
| 505 |
+
"grad_norm": 10.529109691209351,
|
| 506 |
+
"learning_rate": 9.638705581521798e-06,
|
| 507 |
+
"loss": 1.9958,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.21308523409363744,
|
| 512 |
+
"grad_norm": 11.644168043518746,
|
| 513 |
+
"learning_rate": 9.618896238427973e-06,
|
| 514 |
+
"loss": 1.8387,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.21608643457382953,
|
| 519 |
+
"grad_norm": 10.27332830146538,
|
| 520 |
+
"learning_rate": 9.598579705289579e-06,
|
| 521 |
+
"loss": 1.9449,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2190876350540216,
|
| 526 |
+
"grad_norm": 5.679908324076684,
|
| 527 |
+
"learning_rate": 9.577758213016948e-06,
|
| 528 |
+
"loss": 2.0876,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.22208883553421369,
|
| 533 |
+
"grad_norm": 12.59216857148061,
|
| 534 |
+
"learning_rate": 9.55643404796878e-06,
|
| 535 |
+
"loss": 1.6231,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.22509003601440578,
|
| 540 |
+
"grad_norm": 11.87232412833194,
|
| 541 |
+
"learning_rate": 9.534609551701078e-06,
|
| 542 |
+
"loss": 1.7406,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.22809123649459784,
|
| 547 |
+
"grad_norm": 11.39859069066619,
|
| 548 |
+
"learning_rate": 9.512287120710032e-06,
|
| 549 |
+
"loss": 2.1341,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.23109243697478993,
|
| 554 |
+
"grad_norm": 9.182462389068496,
|
| 555 |
+
"learning_rate": 9.489469206168863e-06,
|
| 556 |
+
"loss": 1.8263,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.234093637454982,
|
| 561 |
+
"grad_norm": 7.77593574851048,
|
| 562 |
+
"learning_rate": 9.466158313658665e-06,
|
| 563 |
+
"loss": 2.0274,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.23709483793517408,
|
| 568 |
+
"grad_norm": 9.473304898118002,
|
| 569 |
+
"learning_rate": 9.442357002893275e-06,
|
| 570 |
+
"loss": 1.7858,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.24009603841536614,
|
| 575 |
+
"grad_norm": 12.918279823767726,
|
| 576 |
+
"learning_rate": 9.418067887438194e-06,
|
| 577 |
+
"loss": 1.9741,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.24309723889555823,
|
| 582 |
+
"grad_norm": 16.087139659433475,
|
| 583 |
+
"learning_rate": 9.393293634423604e-06,
|
| 584 |
+
"loss": 2.0156,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2460984393757503,
|
| 589 |
+
"grad_norm": 12.503098107833772,
|
| 590 |
+
"learning_rate": 9.368036964251488e-06,
|
| 591 |
+
"loss": 1.8051,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.24909963985594238,
|
| 596 |
+
"grad_norm": 17.921159341402873,
|
| 597 |
+
"learning_rate": 9.342300650296911e-06,
|
| 598 |
+
"loss": 2.0905,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.25210084033613445,
|
| 603 |
+
"grad_norm": 8.181948558613119,
|
| 604 |
+
"learning_rate": 9.316087518603491e-06,
|
| 605 |
+
"loss": 2.1614,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.25510204081632654,
|
| 610 |
+
"grad_norm": 12.386120651762177,
|
| 611 |
+
"learning_rate": 9.289400447573068e-06,
|
| 612 |
+
"loss": 1.9288,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.2581032412965186,
|
| 617 |
+
"grad_norm": 12.82368671615243,
|
| 618 |
+
"learning_rate": 9.262242367649637e-06,
|
| 619 |
+
"loss": 1.8841,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.26110444177671066,
|
| 624 |
+
"grad_norm": 11.682775075383281,
|
| 625 |
+
"learning_rate": 9.23461626099756e-06,
|
| 626 |
+
"loss": 1.8096,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.26410564225690275,
|
| 631 |
+
"grad_norm": 10.977666012081006,
|
| 632 |
+
"learning_rate": 9.20652516117411e-06,
|
| 633 |
+
"loss": 2.0035,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.26710684273709484,
|
| 638 |
+
"grad_norm": 10.140829194373916,
|
| 639 |
+
"learning_rate": 9.177972152796352e-06,
|
| 640 |
+
"loss": 1.8845,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.27010804321728693,
|
| 645 |
+
"grad_norm": 11.31872075294124,
|
| 646 |
+
"learning_rate": 9.148960371202442e-06,
|
| 647 |
+
"loss": 2.1503,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.27310924369747897,
|
| 652 |
+
"grad_norm": 15.07747778104917,
|
| 653 |
+
"learning_rate": 9.119493002107325e-06,
|
| 654 |
+
"loss": 2.1282,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.27611044417767105,
|
| 659 |
+
"grad_norm": 14.623330843128887,
|
| 660 |
+
"learning_rate": 9.089573281252938e-06,
|
| 661 |
+
"loss": 1.836,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.27911164465786314,
|
| 666 |
+
"grad_norm": 9.349353118072754,
|
| 667 |
+
"learning_rate": 9.059204494052884e-06,
|
| 668 |
+
"loss": 2.0206,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.28211284513805523,
|
| 673 |
+
"grad_norm": 13.132253499401044,
|
| 674 |
+
"learning_rate": 9.028389975231687e-06,
|
| 675 |
+
"loss": 2.0025,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2851140456182473,
|
| 680 |
+
"grad_norm": 8.77966207647504,
|
| 681 |
+
"learning_rate": 8.997133108458594e-06,
|
| 682 |
+
"loss": 2.0201,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.28811524609843936,
|
| 687 |
+
"grad_norm": 7.676366705721278,
|
| 688 |
+
"learning_rate": 8.965437325976036e-06,
|
| 689 |
+
"loss": 1.8401,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.29111644657863145,
|
| 694 |
+
"grad_norm": 17.688333111422782,
|
| 695 |
+
"learning_rate": 8.93330610822274e-06,
|
| 696 |
+
"loss": 1.7173,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.29411764705882354,
|
| 701 |
+
"grad_norm": 10.818948813957974,
|
| 702 |
+
"learning_rate": 8.900742983451538e-06,
|
| 703 |
+
"loss": 2.2006,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.29711884753901563,
|
| 708 |
+
"grad_norm": 10.149928390127263,
|
| 709 |
+
"learning_rate": 8.867751527341962e-06,
|
| 710 |
+
"loss": 2.0095,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.30012004801920766,
|
| 715 |
+
"grad_norm": 8.46959243433518,
|
| 716 |
+
"learning_rate": 8.834335362607578e-06,
|
| 717 |
+
"loss": 1.8346,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.30012004801920766,
|
| 722 |
+
"eval_loss": 1.8436174392700195,
|
| 723 |
+
"eval_runtime": 70.088,
|
| 724 |
+
"eval_samples_per_second": 21.131,
|
| 725 |
+
"eval_steps_per_second": 10.572,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.30312124849939975,
|
| 730 |
+
"grad_norm": 16.868801651903272,
|
| 731 |
+
"learning_rate": 8.80049815859821e-06,
|
| 732 |
+
"loss": 1.9479,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.30612244897959184,
|
| 737 |
+
"grad_norm": 10.50023341524374,
|
| 738 |
+
"learning_rate": 8.766243630897002e-06,
|
| 739 |
+
"loss": 2.1128,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.30912364945978393,
|
| 744 |
+
"grad_norm": 8.928156526275373,
|
| 745 |
+
"learning_rate": 8.731575540912422e-06,
|
| 746 |
+
"loss": 1.9959,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.31212484993997597,
|
| 751 |
+
"grad_norm": 11.834343384295739,
|
| 752 |
+
"learning_rate": 8.696497695465237e-06,
|
| 753 |
+
"loss": 1.8446,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.31512605042016806,
|
| 758 |
+
"grad_norm": 14.438889863331674,
|
| 759 |
+
"learning_rate": 8.66101394637048e-06,
|
| 760 |
+
"loss": 1.9538,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.31812725090036015,
|
| 765 |
+
"grad_norm": 7.0509264901284405,
|
| 766 |
+
"learning_rate": 8.625128190014513e-06,
|
| 767 |
+
"loss": 2.224,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.32112845138055224,
|
| 772 |
+
"grad_norm": 10.882784743186303,
|
| 773 |
+
"learning_rate": 8.588844366927156e-06,
|
| 774 |
+
"loss": 1.9669,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3241296518607443,
|
| 779 |
+
"grad_norm": 8.990237158612308,
|
| 780 |
+
"learning_rate": 8.552166461348991e-06,
|
| 781 |
+
"loss": 1.7175,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.32713085234093636,
|
| 786 |
+
"grad_norm": 14.10485370212862,
|
| 787 |
+
"learning_rate": 8.515098500793868e-06,
|
| 788 |
+
"loss": 1.9135,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.33013205282112845,
|
| 793 |
+
"grad_norm": 11.4270403766335,
|
| 794 |
+
"learning_rate": 8.477644555606647e-06,
|
| 795 |
+
"loss": 1.9181,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.33313325330132054,
|
| 800 |
+
"grad_norm": 10.98863933462178,
|
| 801 |
+
"learning_rate": 8.439808738516248e-06,
|
| 802 |
+
"loss": 2.0249,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.33613445378151263,
|
| 807 |
+
"grad_norm": 21.402837855150903,
|
| 808 |
+
"learning_rate": 8.401595204184035e-06,
|
| 809 |
+
"loss": 1.7287,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.33913565426170467,
|
| 814 |
+
"grad_norm": 13.977226200369794,
|
| 815 |
+
"learning_rate": 8.363008148747606e-06,
|
| 816 |
+
"loss": 1.7275,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.34213685474189676,
|
| 821 |
+
"grad_norm": 12.329315260812974,
|
| 822 |
+
"learning_rate": 8.324051809360037e-06,
|
| 823 |
+
"loss": 1.9854,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.34513805522208885,
|
| 828 |
+
"grad_norm": 6.8949526667461125,
|
| 829 |
+
"learning_rate": 8.284730463724585e-06,
|
| 830 |
+
"loss": 1.8173,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.34813925570228094,
|
| 835 |
+
"grad_norm": 15.132137249007318,
|
| 836 |
+
"learning_rate": 8.245048429624983e-06,
|
| 837 |
+
"loss": 2.0162,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.35114045618247297,
|
| 842 |
+
"grad_norm": 11.463625138426867,
|
| 843 |
+
"learning_rate": 8.205010064451314e-06,
|
| 844 |
+
"loss": 2.2115,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.35414165666266506,
|
| 849 |
+
"grad_norm": 12.725809570070531,
|
| 850 |
+
"learning_rate": 8.164619764721523e-06,
|
| 851 |
+
"loss": 2.204,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.35714285714285715,
|
| 856 |
+
"grad_norm": 12.730243560834372,
|
| 857 |
+
"learning_rate": 8.12388196559866e-06,
|
| 858 |
+
"loss": 1.897,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.36014405762304924,
|
| 863 |
+
"grad_norm": 7.029827177766862,
|
| 864 |
+
"learning_rate": 8.082801140403857e-06,
|
| 865 |
+
"loss": 1.7744,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.3631452581032413,
|
| 870 |
+
"grad_norm": 10.414460517503901,
|
| 871 |
+
"learning_rate": 8.041381800125129e-06,
|
| 872 |
+
"loss": 1.8452,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.36614645858343337,
|
| 877 |
+
"grad_norm": 13.745072092763401,
|
| 878 |
+
"learning_rate": 7.999628492922022e-06,
|
| 879 |
+
"loss": 2.0646,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.36914765906362546,
|
| 884 |
+
"grad_norm": 8.775551099349842,
|
| 885 |
+
"learning_rate": 7.957545803626208e-06,
|
| 886 |
+
"loss": 1.9013,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.37214885954381755,
|
| 891 |
+
"grad_norm": 12.599490709310933,
|
| 892 |
+
"learning_rate": 7.915138353238018e-06,
|
| 893 |
+
"loss": 2.0367,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.3751500600240096,
|
| 898 |
+
"grad_norm": 6.256535396667515,
|
| 899 |
+
"learning_rate": 7.872410798419033e-06,
|
| 900 |
+
"loss": 1.9974,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.37815126050420167,
|
| 905 |
+
"grad_norm": 9.33884703529061,
|
| 906 |
+
"learning_rate": 7.829367830980739e-06,
|
| 907 |
+
"loss": 1.9962,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.38115246098439376,
|
| 912 |
+
"grad_norm": 21.706114177368843,
|
| 913 |
+
"learning_rate": 7.786014177369336e-06,
|
| 914 |
+
"loss": 1.9969,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.38415366146458585,
|
| 919 |
+
"grad_norm": 12.19292284047377,
|
| 920 |
+
"learning_rate": 7.742354598146737e-06,
|
| 921 |
+
"loss": 2.0981,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3871548619447779,
|
| 926 |
+
"grad_norm": 9.306186302055167,
|
| 927 |
+
"learning_rate": 7.698393887467822e-06,
|
| 928 |
+
"loss": 1.9351,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.39015606242497,
|
| 933 |
+
"grad_norm": 7.075234259359012,
|
| 934 |
+
"learning_rate": 7.654136872553994e-06,
|
| 935 |
+
"loss": 2.0849,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.39315726290516206,
|
| 940 |
+
"grad_norm": 13.098710223009212,
|
| 941 |
+
"learning_rate": 7.609588413163133e-06,
|
| 942 |
+
"loss": 2.1268,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.39615846338535415,
|
| 947 |
+
"grad_norm": 8.116612120897077,
|
| 948 |
+
"learning_rate": 7.564753401055938e-06,
|
| 949 |
+
"loss": 2.1511,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.39915966386554624,
|
| 954 |
+
"grad_norm": 11.134740327279541,
|
| 955 |
+
"learning_rate": 7.519636759458787e-06,
|
| 956 |
+
"loss": 1.8251,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4021608643457383,
|
| 961 |
+
"grad_norm": 7.351044801101755,
|
| 962 |
+
"learning_rate": 7.474243442523122e-06,
|
| 963 |
+
"loss": 1.9105,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.40516206482593037,
|
| 968 |
+
"grad_norm": 13.084121400843905,
|
| 969 |
+
"learning_rate": 7.428578434781446e-06,
|
| 970 |
+
"loss": 2.0436,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.40816326530612246,
|
| 975 |
+
"grad_norm": 9.072398206431368,
|
| 976 |
+
"learning_rate": 7.382646750599991e-06,
|
| 977 |
+
"loss": 1.9403,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.41116446578631455,
|
| 982 |
+
"grad_norm": 10.586715140991426,
|
| 983 |
+
"learning_rate": 7.33645343362809e-06,
|
| 984 |
+
"loss": 2.0718,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.4141656662665066,
|
| 989 |
+
"grad_norm": 11.515109253824,
|
| 990 |
+
"learning_rate": 7.290003556244359e-06,
|
| 991 |
+
"loss": 1.8263,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4171668667466987,
|
| 996 |
+
"grad_norm": 11.730876807196703,
|
| 997 |
+
"learning_rate": 7.2433022189997e-06,
|
| 998 |
+
"loss": 1.9503,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.42016806722689076,
|
| 1003 |
+
"grad_norm": 10.550292645454324,
|
| 1004 |
+
"learning_rate": 7.196354550057226e-06,
|
| 1005 |
+
"loss": 1.8239,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.42316926770708285,
|
| 1010 |
+
"grad_norm": 9.887874814498124,
|
| 1011 |
+
"learning_rate": 7.1491657046291526e-06,
|
| 1012 |
+
"loss": 1.9299,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4261704681872749,
|
| 1017 |
+
"grad_norm": 12.616008529269662,
|
| 1018 |
+
"learning_rate": 7.101740864410709e-06,
|
| 1019 |
+
"loss": 2.1525,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.429171668667467,
|
| 1024 |
+
"grad_norm": 8.812376323246953,
|
| 1025 |
+
"learning_rate": 7.05408523701116e-06,
|
| 1026 |
+
"loss": 1.8238,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.43217286914765907,
|
| 1031 |
+
"grad_norm": 8.745128290955817,
|
| 1032 |
+
"learning_rate": 7.006204055381957e-06,
|
| 1033 |
+
"loss": 1.6758,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.43517406962785116,
|
| 1038 |
+
"grad_norm": 6.318402234130335,
|
| 1039 |
+
"learning_rate": 6.958102577242128e-06,
|
| 1040 |
+
"loss": 1.9202,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.4381752701080432,
|
| 1045 |
+
"grad_norm": 7.927574856182854,
|
| 1046 |
+
"learning_rate": 6.909786084500939e-06,
|
| 1047 |
+
"loss": 2.0833,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4411764705882353,
|
| 1052 |
+
"grad_norm": 10.544936971680398,
|
| 1053 |
+
"learning_rate": 6.861259882677902e-06,
|
| 1054 |
+
"loss": 2.002,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.44417767106842737,
|
| 1059 |
+
"grad_norm": 11.619710218418861,
|
| 1060 |
+
"learning_rate": 6.8125293003201806e-06,
|
| 1061 |
+
"loss": 1.7993,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.44717887154861946,
|
| 1066 |
+
"grad_norm": 6.420503958767878,
|
| 1067 |
+
"learning_rate": 6.763599688417487e-06,
|
| 1068 |
+
"loss": 1.8841,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.45018007202881155,
|
| 1073 |
+
"grad_norm": 12.533300979520721,
|
| 1074 |
+
"learning_rate": 6.714476419814492e-06,
|
| 1075 |
+
"loss": 1.9325,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.45018007202881155,
|
| 1080 |
+
"eval_loss": 1.7854255437850952,
|
| 1081 |
+
"eval_runtime": 72.7355,
|
| 1082 |
+
"eval_samples_per_second": 20.361,
|
| 1083 |
+
"eval_steps_per_second": 10.188,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.4531812725090036,
|
| 1088 |
+
"grad_norm": 4.747847172239305,
|
| 1089 |
+
"learning_rate": 6.665164888620848e-06,
|
| 1090 |
+
"loss": 1.6663,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.4561824729891957,
|
| 1095 |
+
"grad_norm": 7.525229479358654,
|
| 1096 |
+
"learning_rate": 6.615670509618879e-06,
|
| 1097 |
+
"loss": 1.6184,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.45918367346938777,
|
| 1102 |
+
"grad_norm": 9.73553436099885,
|
| 1103 |
+
"learning_rate": 6.565998717668992e-06,
|
| 1104 |
+
"loss": 2.0157,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.46218487394957986,
|
| 1109 |
+
"grad_norm": 1.9365788113666345,
|
| 1110 |
+
"learning_rate": 6.516154967112891e-06,
|
| 1111 |
+
"loss": 1.5343,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.4651860744297719,
|
| 1116 |
+
"grad_norm": 13.65674435295188,
|
| 1117 |
+
"learning_rate": 6.466144731174645e-06,
|
| 1118 |
+
"loss": 1.8785,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.468187274909964,
|
| 1123 |
+
"grad_norm": 12.365721091880623,
|
| 1124 |
+
"learning_rate": 6.415973501359687e-06,
|
| 1125 |
+
"loss": 1.7204,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.47118847539015607,
|
| 1130 |
+
"grad_norm": 6.498996459559609,
|
| 1131 |
+
"learning_rate": 6.365646786851809e-06,
|
| 1132 |
+
"loss": 1.9123,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.47418967587034816,
|
| 1137 |
+
"grad_norm": 12.248966426285023,
|
| 1138 |
+
"learning_rate": 6.315170113908204e-06,
|
| 1139 |
+
"loss": 2.0724,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.4771908763505402,
|
| 1144 |
+
"grad_norm": 6.254751069477799,
|
| 1145 |
+
"learning_rate": 6.264549025252652e-06,
|
| 1146 |
+
"loss": 2.0417,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4801920768307323,
|
| 1151 |
+
"grad_norm": 11.586505827936087,
|
| 1152 |
+
"learning_rate": 6.213789079466873e-06,
|
| 1153 |
+
"loss": 1.9998,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4831932773109244,
|
| 1158 |
+
"grad_norm": 11.628169667737911,
|
| 1159 |
+
"learning_rate": 6.1628958503801635e-06,
|
| 1160 |
+
"loss": 1.9805,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.48619447779111646,
|
| 1165 |
+
"grad_norm": 10.266695075168396,
|
| 1166 |
+
"learning_rate": 6.111874926457344e-06,
|
| 1167 |
+
"loss": 1.9866,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.4891956782713085,
|
| 1172 |
+
"grad_norm": 7.864602445607685,
|
| 1173 |
+
"learning_rate": 6.0607319101850955e-06,
|
| 1174 |
+
"loss": 2.0325,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4921968787515006,
|
| 1179 |
+
"grad_norm": 7.852131699169073,
|
| 1180 |
+
"learning_rate": 6.009472417456779e-06,
|
| 1181 |
+
"loss": 2.136,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4951980792316927,
|
| 1186 |
+
"grad_norm": 9.171127473935298,
|
| 1187 |
+
"learning_rate": 5.958102076955753e-06,
|
| 1188 |
+
"loss": 1.8371,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.49819927971188477,
|
| 1193 |
+
"grad_norm": 13.155484650564988,
|
| 1194 |
+
"learning_rate": 5.906626529537311e-06,
|
| 1195 |
+
"loss": 2.1112,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.5012004801920769,
|
| 1200 |
+
"grad_norm": 14.407405269785295,
|
| 1201 |
+
"learning_rate": 5.855051427609265e-06,
|
| 1202 |
+
"loss": 2.1317,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.5042016806722689,
|
| 1207 |
+
"grad_norm": 7.944398594556855,
|
| 1208 |
+
"learning_rate": 5.803382434511274e-06,
|
| 1209 |
+
"loss": 1.9131,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.507202881152461,
|
| 1214 |
+
"grad_norm": 12.067931060345453,
|
| 1215 |
+
"learning_rate": 5.751625223892964e-06,
|
| 1216 |
+
"loss": 1.961,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.5102040816326531,
|
| 1221 |
+
"grad_norm": 11.305421590297874,
|
| 1222 |
+
"learning_rate": 5.699785479090917e-06,
|
| 1223 |
+
"loss": 1.8233,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.5132052821128451,
|
| 1228 |
+
"grad_norm": 10.568805120830348,
|
| 1229 |
+
"learning_rate": 5.647868892504597e-06,
|
| 1230 |
+
"loss": 1.8034,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.5162064825930373,
|
| 1235 |
+
"grad_norm": 8.901920906884708,
|
| 1236 |
+
"learning_rate": 5.595881164971284e-06,
|
| 1237 |
+
"loss": 2.1088,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.5192076830732293,
|
| 1242 |
+
"grad_norm": 10.818151872015115,
|
| 1243 |
+
"learning_rate": 5.543828005140076e-06,
|
| 1244 |
+
"loss": 1.9505,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.5222088835534213,
|
| 1249 |
+
"grad_norm": 19.0269528128246,
|
| 1250 |
+
"learning_rate": 5.491715128845037e-06,
|
| 1251 |
+
"loss": 2.1158,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.5252100840336135,
|
| 1256 |
+
"grad_norm": 6.368156672789348,
|
| 1257 |
+
"learning_rate": 5.439548258477549e-06,
|
| 1258 |
+
"loss": 1.526,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.5282112845138055,
|
| 1263 |
+
"grad_norm": 14.33226946197169,
|
| 1264 |
+
"learning_rate": 5.387333122357966e-06,
|
| 1265 |
+
"loss": 1.9441,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5312124849939976,
|
| 1270 |
+
"grad_norm": 10.893640588904004,
|
| 1271 |
+
"learning_rate": 5.3350754541065805e-06,
|
| 1272 |
+
"loss": 1.5771,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5342136854741897,
|
| 1277 |
+
"grad_norm": 11.613038829759443,
|
| 1278 |
+
"learning_rate": 5.282780992014043e-06,
|
| 1279 |
+
"loss": 1.8335,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.5372148859543817,
|
| 1284 |
+
"grad_norm": 6.446614047723568,
|
| 1285 |
+
"learning_rate": 5.230455478411243e-06,
|
| 1286 |
+
"loss": 1.9638,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5402160864345739,
|
| 1291 |
+
"grad_norm": 14.258595482993,
|
| 1292 |
+
"learning_rate": 5.1781046590387675e-06,
|
| 1293 |
+
"loss": 1.8887,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.5432172869147659,
|
| 1298 |
+
"grad_norm": 10.102795668494593,
|
| 1299 |
+
"learning_rate": 5.125734282415967e-06,
|
| 1300 |
+
"loss": 2.1767,
|
| 1301 |
+
"step": 1810
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5462184873949579,
|
| 1305 |
+
"grad_norm": 11.29991368417218,
|
| 1306 |
+
"learning_rate": 5.0733500992097295e-06,
|
| 1307 |
+
"loss": 1.8136,
|
| 1308 |
+
"step": 1820
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.5492196878751501,
|
| 1312 |
+
"grad_norm": 5.146344981754679,
|
| 1313 |
+
"learning_rate": 5.020957861603011e-06,
|
| 1314 |
+
"loss": 1.6411,
|
| 1315 |
+
"step": 1830
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5522208883553421,
|
| 1319 |
+
"grad_norm": 14.066643454727922,
|
| 1320 |
+
"learning_rate": 4.9685633226632004e-06,
|
| 1321 |
+
"loss": 1.8657,
|
| 1322 |
+
"step": 1840
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5552220888355343,
|
| 1326 |
+
"grad_norm": 9.885151028744932,
|
| 1327 |
+
"learning_rate": 4.916172235710393e-06,
|
| 1328 |
+
"loss": 1.8143,
|
| 1329 |
+
"step": 1850
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5582232893157263,
|
| 1333 |
+
"grad_norm": 11.550762892952077,
|
| 1334 |
+
"learning_rate": 4.8637903536856266e-06,
|
| 1335 |
+
"loss": 1.9513,
|
| 1336 |
+
"step": 1860
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5612244897959183,
|
| 1340 |
+
"grad_norm": 16.261531223174785,
|
| 1341 |
+
"learning_rate": 4.811423428519169e-06,
|
| 1342 |
+
"loss": 1.6205,
|
| 1343 |
+
"step": 1870
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5642256902761105,
|
| 1347 |
+
"grad_norm": 11.38322225643573,
|
| 1348 |
+
"learning_rate": 4.759077210498913e-06,
|
| 1349 |
+
"loss": 1.7196,
|
| 1350 |
+
"step": 1880
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5672268907563025,
|
| 1354 |
+
"grad_norm": 8.776094085092314,
|
| 1355 |
+
"learning_rate": 4.706757447638945e-06,
|
| 1356 |
+
"loss": 2.0409,
|
| 1357 |
+
"step": 1890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5702280912364946,
|
| 1361 |
+
"grad_norm": 9.049484315692625,
|
| 1362 |
+
"learning_rate": 4.654469885048376e-06,
|
| 1363 |
+
"loss": 1.9866,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.5732292917166867,
|
| 1368 |
+
"grad_norm": 10.657785810994662,
|
| 1369 |
+
"learning_rate": 4.602220264300481e-06,
|
| 1370 |
+
"loss": 1.8922,
|
| 1371 |
+
"step": 1910
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5762304921968787,
|
| 1375 |
+
"grad_norm": 9.342865110666766,
|
| 1376 |
+
"learning_rate": 4.55001432280223e-06,
|
| 1377 |
+
"loss": 1.7542,
|
| 1378 |
+
"step": 1920
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5792316926770709,
|
| 1382 |
+
"grad_norm": 12.081799903070168,
|
| 1383 |
+
"learning_rate": 4.497857793164277e-06,
|
| 1384 |
+
"loss": 1.9913,
|
| 1385 |
+
"step": 1930
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5822328931572629,
|
| 1389 |
+
"grad_norm": 7.619917781656242,
|
| 1390 |
+
"learning_rate": 4.445756402571483e-06,
|
| 1391 |
+
"loss": 1.9881,
|
| 1392 |
+
"step": 1940
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5852340936374549,
|
| 1396 |
+
"grad_norm": 9.093969376778242,
|
| 1397 |
+
"learning_rate": 4.393715872154014e-06,
|
| 1398 |
+
"loss": 1.7711,
|
| 1399 |
+
"step": 1950
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5882352941176471,
|
| 1403 |
+
"grad_norm": 9.108154177538303,
|
| 1404 |
+
"learning_rate": 4.3417419163591296e-06,
|
| 1405 |
+
"loss": 1.7914,
|
| 1406 |
+
"step": 1960
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5912364945978391,
|
| 1410 |
+
"grad_norm": 9.864863366342805,
|
| 1411 |
+
"learning_rate": 4.2898402423236835e-06,
|
| 1412 |
+
"loss": 1.7734,
|
| 1413 |
+
"step": 1970
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5942376950780313,
|
| 1417 |
+
"grad_norm": 14.65031277951791,
|
| 1418 |
+
"learning_rate": 4.238016549247443e-06,
|
| 1419 |
+
"loss": 1.8682,
|
| 1420 |
+
"step": 1980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.5972388955582233,
|
| 1424 |
+
"grad_norm": 15.195046706414468,
|
| 1425 |
+
"learning_rate": 4.186276527767273e-06,
|
| 1426 |
+
"loss": 1.8358,
|
| 1427 |
+
"step": 1990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.6002400960384153,
|
| 1431 |
+
"grad_norm": 7.420521707718542,
|
| 1432 |
+
"learning_rate": 4.1346258593322555e-06,
|
| 1433 |
+
"loss": 1.8923,
|
| 1434 |
+
"step": 2000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.6002400960384153,
|
| 1438 |
+
"eval_loss": 1.7435638904571533,
|
| 1439 |
+
"eval_runtime": 69.2816,
|
| 1440 |
+
"eval_samples_per_second": 21.377,
|
| 1441 |
+
"eval_steps_per_second": 10.695,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.6032412965186075,
|
| 1446 |
+
"grad_norm": 25.45598758249549,
|
| 1447 |
+
"learning_rate": 4.08307021557983e-06,
|
| 1448 |
+
"loss": 1.7191,
|
| 1449 |
+
"step": 2010
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.6062424969987995,
|
| 1453 |
+
"grad_norm": 7.897349852896533,
|
| 1454 |
+
"learning_rate": 4.031615257712996e-06,
|
| 1455 |
+
"loss": 1.9881,
|
| 1456 |
+
"step": 2020
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.6092436974789915,
|
| 1460 |
+
"grad_norm": 6.16625120190022,
|
| 1461 |
+
"learning_rate": 3.98026663587868e-06,
|
| 1462 |
+
"loss": 1.7836,
|
| 1463 |
+
"step": 2030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.6122448979591837,
|
| 1467 |
+
"grad_norm": 20.615497493186695,
|
| 1468 |
+
"learning_rate": 3.929029988547296e-06,
|
| 1469 |
+
"loss": 1.9693,
|
| 1470 |
+
"step": 2040
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.6152460984393757,
|
| 1474 |
+
"grad_norm": 16.331083465757896,
|
| 1475 |
+
"learning_rate": 3.8779109418936074e-06,
|
| 1476 |
+
"loss": 1.9877,
|
| 1477 |
+
"step": 2050
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.6182472989195679,
|
| 1481 |
+
"grad_norm": 8.975255093028004,
|
| 1482 |
+
"learning_rate": 3.826915109178925e-06,
|
| 1483 |
+
"loss": 1.7951,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.6212484993997599,
|
| 1488 |
+
"grad_norm": 14.614156710342609,
|
| 1489 |
+
"learning_rate": 3.776048090134726e-06,
|
| 1490 |
+
"loss": 2.0532,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.6242496998799519,
|
| 1495 |
+
"grad_norm": 14.227607937991625,
|
| 1496 |
+
"learning_rate": 3.725315470347769e-06,
|
| 1497 |
+
"loss": 1.6202,
|
| 1498 |
+
"step": 2080
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.6272509003601441,
|
| 1502 |
+
"grad_norm": 9.755464711787543,
|
| 1503 |
+
"learning_rate": 3.6747228206467435e-06,
|
| 1504 |
+
"loss": 1.8552,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.6302521008403361,
|
| 1509 |
+
"grad_norm": 11.720295448594253,
|
| 1510 |
+
"learning_rate": 3.62427569649056e-06,
|
| 1511 |
+
"loss": 2.0746,
|
| 1512 |
+
"step": 2100
|
| 1513 |
+
}
|
| 1514 |
+
],
|
| 1515 |
+
"logging_steps": 10,
|
| 1516 |
+
"max_steps": 3332,
|
| 1517 |
+
"num_input_tokens_seen": 0,
|
| 1518 |
+
"num_train_epochs": 1,
|
| 1519 |
+
"save_steps": 100,
|
| 1520 |
+
"stateful_callbacks": {
|
| 1521 |
+
"TrainerControl": {
|
| 1522 |
+
"args": {
|
| 1523 |
+
"should_epoch_stop": false,
|
| 1524 |
+
"should_evaluate": false,
|
| 1525 |
+
"should_log": false,
|
| 1526 |
+
"should_save": true,
|
| 1527 |
+
"should_training_stop": false
|
| 1528 |
+
},
|
| 1529 |
+
"attributes": {}
|
| 1530 |
+
}
|
| 1531 |
+
},
|
| 1532 |
+
"total_flos": 2420773355520.0,
|
| 1533 |
+
"train_batch_size": 2,
|
| 1534 |
+
"trial_name": null,
|
| 1535 |
+
"trial_params": null
|
| 1536 |
+
}
|
checkpoint-2200/chat_template.jinja
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
|
| 2 |
+
' + message['content'] + '
|
| 3 |
+
' }}{% elif message['role'] == 'user' %}{{ '<|user|>
|
| 4 |
+
' + message['content'] + '
|
| 5 |
+
' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
|
| 6 |
+
' + message['content'] + eos_token + '
|
| 7 |
+
' }}{% else %}{{ '<|assistant|>
|
| 8 |
+
' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
|
| 9 |
+
' }}{% endif %}{% endfor %}
|
checkpoint-2200/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-2200/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-2200/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step2200
|
checkpoint-2200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-2200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 186 |
+
"pad_token": "<|pad|>",
|
| 187 |
+
"padding_side": "right",
|
| 188 |
+
"split_special_tokens": false,
|
| 189 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 190 |
+
"unk_token": "<|endoftext|>"
|
| 191 |
+
}
|
checkpoint-2200/trainer_state.json
ADDED
|
@@ -0,0 +1,1606 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6602641056422569,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003001200480192077,
|
| 14 |
+
"grad_norm": 16.322778038786794,
|
| 15 |
+
"learning_rate": 2.694610778443114e-07,
|
| 16 |
+
"loss": 2.4961,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.006002400960384154,
|
| 21 |
+
"grad_norm": 21.26487128326307,
|
| 22 |
+
"learning_rate": 5.688622754491019e-07,
|
| 23 |
+
"loss": 2.4545,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00900360144057623,
|
| 28 |
+
"grad_norm": 20.493921349321404,
|
| 29 |
+
"learning_rate": 8.682634730538923e-07,
|
| 30 |
+
"loss": 2.4459,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.012004801920768308,
|
| 35 |
+
"grad_norm": 16.939655978226025,
|
| 36 |
+
"learning_rate": 1.1676646706586827e-06,
|
| 37 |
+
"loss": 2.4742,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.015006002400960384,
|
| 42 |
+
"grad_norm": 23.865531522300767,
|
| 43 |
+
"learning_rate": 1.4670658682634732e-06,
|
| 44 |
+
"loss": 2.0074,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01800720288115246,
|
| 49 |
+
"grad_norm": 16.606288718277256,
|
| 50 |
+
"learning_rate": 1.7664670658682636e-06,
|
| 51 |
+
"loss": 1.7784,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02100840336134454,
|
| 56 |
+
"grad_norm": 14.41517087399792,
|
| 57 |
+
"learning_rate": 2.065868263473054e-06,
|
| 58 |
+
"loss": 2.1435,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.024009603841536616,
|
| 63 |
+
"grad_norm": 9.610371534852842,
|
| 64 |
+
"learning_rate": 2.3652694610778446e-06,
|
| 65 |
+
"loss": 1.8848,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02701080432172869,
|
| 70 |
+
"grad_norm": 11.723596844563824,
|
| 71 |
+
"learning_rate": 2.664670658682635e-06,
|
| 72 |
+
"loss": 2.2553,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.030012004801920768,
|
| 77 |
+
"grad_norm": 28.025837302158916,
|
| 78 |
+
"learning_rate": 2.9640718562874255e-06,
|
| 79 |
+
"loss": 1.9136,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.033013205282112844,
|
| 84 |
+
"grad_norm": 9.44674022586452,
|
| 85 |
+
"learning_rate": 3.263473053892216e-06,
|
| 86 |
+
"loss": 2.1588,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03601440576230492,
|
| 91 |
+
"grad_norm": 12.826206690198743,
|
| 92 |
+
"learning_rate": 3.562874251497006e-06,
|
| 93 |
+
"loss": 1.9439,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.039015606242496996,
|
| 98 |
+
"grad_norm": 13.332854551269488,
|
| 99 |
+
"learning_rate": 3.862275449101797e-06,
|
| 100 |
+
"loss": 1.9872,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.04201680672268908,
|
| 105 |
+
"grad_norm": 13.687005134844258,
|
| 106 |
+
"learning_rate": 4.161676646706587e-06,
|
| 107 |
+
"loss": 2.018,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.045018007202881155,
|
| 112 |
+
"grad_norm": 11.10704695361387,
|
| 113 |
+
"learning_rate": 4.461077844311378e-06,
|
| 114 |
+
"loss": 1.8614,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.04801920768307323,
|
| 119 |
+
"grad_norm": 18.355044203461766,
|
| 120 |
+
"learning_rate": 4.760479041916168e-06,
|
| 121 |
+
"loss": 1.961,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05102040816326531,
|
| 126 |
+
"grad_norm": 15.09389345242339,
|
| 127 |
+
"learning_rate": 5.059880239520959e-06,
|
| 128 |
+
"loss": 2.21,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05402160864345738,
|
| 133 |
+
"grad_norm": 10.156004340051048,
|
| 134 |
+
"learning_rate": 5.359281437125749e-06,
|
| 135 |
+
"loss": 2.1261,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05702280912364946,
|
| 140 |
+
"grad_norm": 15.345968230792714,
|
| 141 |
+
"learning_rate": 5.658682634730539e-06,
|
| 142 |
+
"loss": 2.0072,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.060024009603841535,
|
| 147 |
+
"grad_norm": 11.153556976885293,
|
| 148 |
+
"learning_rate": 5.95808383233533e-06,
|
| 149 |
+
"loss": 1.9935,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.06302521008403361,
|
| 154 |
+
"grad_norm": 9.491849063073436,
|
| 155 |
+
"learning_rate": 6.25748502994012e-06,
|
| 156 |
+
"loss": 1.6912,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.06602641056422569,
|
| 161 |
+
"grad_norm": 9.775572755148744,
|
| 162 |
+
"learning_rate": 6.556886227544911e-06,
|
| 163 |
+
"loss": 2.2844,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06902761104441776,
|
| 168 |
+
"grad_norm": 10.444304091533951,
|
| 169 |
+
"learning_rate": 6.8562874251497016e-06,
|
| 170 |
+
"loss": 1.9957,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.07202881152460984,
|
| 175 |
+
"grad_norm": 12.315712653283379,
|
| 176 |
+
"learning_rate": 7.155688622754492e-06,
|
| 177 |
+
"loss": 1.718,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07503001200480192,
|
| 182 |
+
"grad_norm": 15.4266884794421,
|
| 183 |
+
"learning_rate": 7.4550898203592825e-06,
|
| 184 |
+
"loss": 1.8986,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07803121248499399,
|
| 189 |
+
"grad_norm": 15.350622303641131,
|
| 190 |
+
"learning_rate": 7.754491017964072e-06,
|
| 191 |
+
"loss": 2.1906,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.08103241296518607,
|
| 196 |
+
"grad_norm": 10.100826281853637,
|
| 197 |
+
"learning_rate": 8.053892215568863e-06,
|
| 198 |
+
"loss": 2.062,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08403361344537816,
|
| 203 |
+
"grad_norm": 9.985084559589948,
|
| 204 |
+
"learning_rate": 8.353293413173653e-06,
|
| 205 |
+
"loss": 2.0219,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08703481392557023,
|
| 210 |
+
"grad_norm": 25.52843769465498,
|
| 211 |
+
"learning_rate": 8.652694610778444e-06,
|
| 212 |
+
"loss": 1.774,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09003601440576231,
|
| 217 |
+
"grad_norm": 7.010526730435224,
|
| 218 |
+
"learning_rate": 8.952095808383234e-06,
|
| 219 |
+
"loss": 1.7647,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.09303721488595439,
|
| 224 |
+
"grad_norm": 10.925177037546252,
|
| 225 |
+
"learning_rate": 9.251497005988024e-06,
|
| 226 |
+
"loss": 1.853,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.09603841536614646,
|
| 231 |
+
"grad_norm": 13.12192108271367,
|
| 232 |
+
"learning_rate": 9.550898203592815e-06,
|
| 233 |
+
"loss": 2.023,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09903961584633854,
|
| 238 |
+
"grad_norm": 19.146417141785633,
|
| 239 |
+
"learning_rate": 9.850299401197606e-06,
|
| 240 |
+
"loss": 1.8804,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.10204081632653061,
|
| 245 |
+
"grad_norm": 17.095401175842863,
|
| 246 |
+
"learning_rate": 9.99993136976086e-06,
|
| 247 |
+
"loss": 2.0625,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.10504201680672269,
|
| 252 |
+
"grad_norm": 14.915026178785793,
|
| 253 |
+
"learning_rate": 9.99938233915195e-06,
|
| 254 |
+
"loss": 1.7554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.10804321728691477,
|
| 259 |
+
"grad_norm": 12.3557938764668,
|
| 260 |
+
"learning_rate": 9.99828433822188e-06,
|
| 261 |
+
"loss": 1.8197,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.11104441776710684,
|
| 266 |
+
"grad_norm": 16.732139399887032,
|
| 267 |
+
"learning_rate": 9.996637487539526e-06,
|
| 268 |
+
"loss": 1.9554,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.11404561824729892,
|
| 273 |
+
"grad_norm": 9.472954878862216,
|
| 274 |
+
"learning_rate": 9.99444196794166e-06,
|
| 275 |
+
"loss": 1.8419,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.117046818727491,
|
| 280 |
+
"grad_norm": 14.45943322716144,
|
| 281 |
+
"learning_rate": 9.99169802051308e-06,
|
| 282 |
+
"loss": 1.9554,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.12004801920768307,
|
| 287 |
+
"grad_norm": 11.816006243448049,
|
| 288 |
+
"learning_rate": 9.988405946560151e-06,
|
| 289 |
+
"loss": 1.6209,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12304921968787515,
|
| 294 |
+
"grad_norm": 19.870456146468612,
|
| 295 |
+
"learning_rate": 9.984566107577707e-06,
|
| 296 |
+
"loss": 2.1652,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.12605042016806722,
|
| 301 |
+
"grad_norm": 15.008106738503946,
|
| 302 |
+
"learning_rate": 9.980178925209363e-06,
|
| 303 |
+
"loss": 1.6964,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1290516206482593,
|
| 308 |
+
"grad_norm": 17.195341077337165,
|
| 309 |
+
"learning_rate": 9.975244881201209e-06,
|
| 310 |
+
"loss": 1.861,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.13205282112845138,
|
| 315 |
+
"grad_norm": 12.45396867483932,
|
| 316 |
+
"learning_rate": 9.969764517348924e-06,
|
| 317 |
+
"loss": 1.7937,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.13505402160864347,
|
| 322 |
+
"grad_norm": 9.707765043650019,
|
| 323 |
+
"learning_rate": 9.963738435438267e-06,
|
| 324 |
+
"loss": 1.956,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.13805522208883553,
|
| 329 |
+
"grad_norm": 12.149984169068404,
|
| 330 |
+
"learning_rate": 9.957167297179004e-06,
|
| 331 |
+
"loss": 1.9112,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.14105642256902762,
|
| 336 |
+
"grad_norm": 11.64329798977207,
|
| 337 |
+
"learning_rate": 9.950051824132247e-06,
|
| 338 |
+
"loss": 2.1092,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.14405762304921968,
|
| 343 |
+
"grad_norm": 13.559828016858319,
|
| 344 |
+
"learning_rate": 9.942392797631222e-06,
|
| 345 |
+
"loss": 2.0729,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14705882352941177,
|
| 350 |
+
"grad_norm": 15.255784576157163,
|
| 351 |
+
"learning_rate": 9.934191058695467e-06,
|
| 352 |
+
"loss": 1.9601,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.15006002400960383,
|
| 357 |
+
"grad_norm": 15.12208631421886,
|
| 358 |
+
"learning_rate": 9.925447507938493e-06,
|
| 359 |
+
"loss": 1.8079,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.15006002400960383,
|
| 364 |
+
"eval_loss": 1.8881598711013794,
|
| 365 |
+
"eval_runtime": 71.4162,
|
| 366 |
+
"eval_samples_per_second": 20.738,
|
| 367 |
+
"eval_steps_per_second": 10.376,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.15306122448979592,
|
| 372 |
+
"grad_norm": 9.812255338971053,
|
| 373 |
+
"learning_rate": 9.916163105468872e-06,
|
| 374 |
+
"loss": 1.9261,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.15606242496998798,
|
| 379 |
+
"grad_norm": 16.56967240161569,
|
| 380 |
+
"learning_rate": 9.90633887078483e-06,
|
| 381 |
+
"loss": 2.1224,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.15906362545018007,
|
| 386 |
+
"grad_norm": 10.921999649807898,
|
| 387 |
+
"learning_rate": 9.895975882662283e-06,
|
| 388 |
+
"loss": 1.7545,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.16206482593037214,
|
| 393 |
+
"grad_norm": 11.686083276616063,
|
| 394 |
+
"learning_rate": 9.885075279036385e-06,
|
| 395 |
+
"loss": 2.0052,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.16506602641056423,
|
| 400 |
+
"grad_norm": 13.670316963331478,
|
| 401 |
+
"learning_rate": 9.873638256876577e-06,
|
| 402 |
+
"loss": 1.8232,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.16806722689075632,
|
| 407 |
+
"grad_norm": 10.550976781841975,
|
| 408 |
+
"learning_rate": 9.861666072055144e-06,
|
| 409 |
+
"loss": 2.0087,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.17106842737094838,
|
| 414 |
+
"grad_norm": 7.518022216683535,
|
| 415 |
+
"learning_rate": 9.849160039209317e-06,
|
| 416 |
+
"loss": 2.0186,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.17406962785114047,
|
| 421 |
+
"grad_norm": 18.610725609857187,
|
| 422 |
+
"learning_rate": 9.83612153159691e-06,
|
| 423 |
+
"loss": 1.9651,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.17707082833133253,
|
| 428 |
+
"grad_norm": 14.468204525410128,
|
| 429 |
+
"learning_rate": 9.822551980945526e-06,
|
| 430 |
+
"loss": 1.8678,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.18007202881152462,
|
| 435 |
+
"grad_norm": 10.68638583134911,
|
| 436 |
+
"learning_rate": 9.808452877295356e-06,
|
| 437 |
+
"loss": 2.1099,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.18307322929171668,
|
| 442 |
+
"grad_norm": 6.8000928033318555,
|
| 443 |
+
"learning_rate": 9.79382576883554e-06,
|
| 444 |
+
"loss": 2.0071,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.18607442977190877,
|
| 449 |
+
"grad_norm": 9.517671427003565,
|
| 450 |
+
"learning_rate": 9.778672261734172e-06,
|
| 451 |
+
"loss": 2.2586,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.18907563025210083,
|
| 456 |
+
"grad_norm": 17.30722139026249,
|
| 457 |
+
"learning_rate": 9.762994019961944e-06,
|
| 458 |
+
"loss": 1.9017,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.19207683073229292,
|
| 463 |
+
"grad_norm": 7.832218568217347,
|
| 464 |
+
"learning_rate": 9.746792765109412e-06,
|
| 465 |
+
"loss": 2.0726,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.195078031212485,
|
| 470 |
+
"grad_norm": 15.595751845972346,
|
| 471 |
+
"learning_rate": 9.730070276197955e-06,
|
| 472 |
+
"loss": 2.1412,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.19807923169267708,
|
| 477 |
+
"grad_norm": 14.534725999964142,
|
| 478 |
+
"learning_rate": 9.712828389484432e-06,
|
| 479 |
+
"loss": 2.0257,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.20108043217286914,
|
| 484 |
+
"grad_norm": 9.963604466793788,
|
| 485 |
+
"learning_rate": 9.695068998259547e-06,
|
| 486 |
+
"loss": 1.9898,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.20408163265306123,
|
| 491 |
+
"grad_norm": 12.040002240054593,
|
| 492 |
+
"learning_rate": 9.676794052639937e-06,
|
| 493 |
+
"loss": 2.2448,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2070828331332533,
|
| 498 |
+
"grad_norm": 15.184552955496128,
|
| 499 |
+
"learning_rate": 9.658005559354053e-06,
|
| 500 |
+
"loss": 1.9303,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.21008403361344538,
|
| 505 |
+
"grad_norm": 10.529109691209351,
|
| 506 |
+
"learning_rate": 9.638705581521798e-06,
|
| 507 |
+
"loss": 1.9958,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.21308523409363744,
|
| 512 |
+
"grad_norm": 11.644168043518746,
|
| 513 |
+
"learning_rate": 9.618896238427973e-06,
|
| 514 |
+
"loss": 1.8387,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.21608643457382953,
|
| 519 |
+
"grad_norm": 10.27332830146538,
|
| 520 |
+
"learning_rate": 9.598579705289579e-06,
|
| 521 |
+
"loss": 1.9449,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2190876350540216,
|
| 526 |
+
"grad_norm": 5.679908324076684,
|
| 527 |
+
"learning_rate": 9.577758213016948e-06,
|
| 528 |
+
"loss": 2.0876,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.22208883553421369,
|
| 533 |
+
"grad_norm": 12.59216857148061,
|
| 534 |
+
"learning_rate": 9.55643404796878e-06,
|
| 535 |
+
"loss": 1.6231,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.22509003601440578,
|
| 540 |
+
"grad_norm": 11.87232412833194,
|
| 541 |
+
"learning_rate": 9.534609551701078e-06,
|
| 542 |
+
"loss": 1.7406,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.22809123649459784,
|
| 547 |
+
"grad_norm": 11.39859069066619,
|
| 548 |
+
"learning_rate": 9.512287120710032e-06,
|
| 549 |
+
"loss": 2.1341,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.23109243697478993,
|
| 554 |
+
"grad_norm": 9.182462389068496,
|
| 555 |
+
"learning_rate": 9.489469206168863e-06,
|
| 556 |
+
"loss": 1.8263,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.234093637454982,
|
| 561 |
+
"grad_norm": 7.77593574851048,
|
| 562 |
+
"learning_rate": 9.466158313658665e-06,
|
| 563 |
+
"loss": 2.0274,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.23709483793517408,
|
| 568 |
+
"grad_norm": 9.473304898118002,
|
| 569 |
+
"learning_rate": 9.442357002893275e-06,
|
| 570 |
+
"loss": 1.7858,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.24009603841536614,
|
| 575 |
+
"grad_norm": 12.918279823767726,
|
| 576 |
+
"learning_rate": 9.418067887438194e-06,
|
| 577 |
+
"loss": 1.9741,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.24309723889555823,
|
| 582 |
+
"grad_norm": 16.087139659433475,
|
| 583 |
+
"learning_rate": 9.393293634423604e-06,
|
| 584 |
+
"loss": 2.0156,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2460984393757503,
|
| 589 |
+
"grad_norm": 12.503098107833772,
|
| 590 |
+
"learning_rate": 9.368036964251488e-06,
|
| 591 |
+
"loss": 1.8051,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.24909963985594238,
|
| 596 |
+
"grad_norm": 17.921159341402873,
|
| 597 |
+
"learning_rate": 9.342300650296911e-06,
|
| 598 |
+
"loss": 2.0905,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.25210084033613445,
|
| 603 |
+
"grad_norm": 8.181948558613119,
|
| 604 |
+
"learning_rate": 9.316087518603491e-06,
|
| 605 |
+
"loss": 2.1614,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.25510204081632654,
|
| 610 |
+
"grad_norm": 12.386120651762177,
|
| 611 |
+
"learning_rate": 9.289400447573068e-06,
|
| 612 |
+
"loss": 1.9288,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.2581032412965186,
|
| 617 |
+
"grad_norm": 12.82368671615243,
|
| 618 |
+
"learning_rate": 9.262242367649637e-06,
|
| 619 |
+
"loss": 1.8841,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.26110444177671066,
|
| 624 |
+
"grad_norm": 11.682775075383281,
|
| 625 |
+
"learning_rate": 9.23461626099756e-06,
|
| 626 |
+
"loss": 1.8096,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.26410564225690275,
|
| 631 |
+
"grad_norm": 10.977666012081006,
|
| 632 |
+
"learning_rate": 9.20652516117411e-06,
|
| 633 |
+
"loss": 2.0035,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.26710684273709484,
|
| 638 |
+
"grad_norm": 10.140829194373916,
|
| 639 |
+
"learning_rate": 9.177972152796352e-06,
|
| 640 |
+
"loss": 1.8845,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.27010804321728693,
|
| 645 |
+
"grad_norm": 11.31872075294124,
|
| 646 |
+
"learning_rate": 9.148960371202442e-06,
|
| 647 |
+
"loss": 2.1503,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.27310924369747897,
|
| 652 |
+
"grad_norm": 15.07747778104917,
|
| 653 |
+
"learning_rate": 9.119493002107325e-06,
|
| 654 |
+
"loss": 2.1282,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.27611044417767105,
|
| 659 |
+
"grad_norm": 14.623330843128887,
|
| 660 |
+
"learning_rate": 9.089573281252938e-06,
|
| 661 |
+
"loss": 1.836,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.27911164465786314,
|
| 666 |
+
"grad_norm": 9.349353118072754,
|
| 667 |
+
"learning_rate": 9.059204494052884e-06,
|
| 668 |
+
"loss": 2.0206,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.28211284513805523,
|
| 673 |
+
"grad_norm": 13.132253499401044,
|
| 674 |
+
"learning_rate": 9.028389975231687e-06,
|
| 675 |
+
"loss": 2.0025,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2851140456182473,
|
| 680 |
+
"grad_norm": 8.77966207647504,
|
| 681 |
+
"learning_rate": 8.997133108458594e-06,
|
| 682 |
+
"loss": 2.0201,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.28811524609843936,
|
| 687 |
+
"grad_norm": 7.676366705721278,
|
| 688 |
+
"learning_rate": 8.965437325976036e-06,
|
| 689 |
+
"loss": 1.8401,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.29111644657863145,
|
| 694 |
+
"grad_norm": 17.688333111422782,
|
| 695 |
+
"learning_rate": 8.93330610822274e-06,
|
| 696 |
+
"loss": 1.7173,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.29411764705882354,
|
| 701 |
+
"grad_norm": 10.818948813957974,
|
| 702 |
+
"learning_rate": 8.900742983451538e-06,
|
| 703 |
+
"loss": 2.2006,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.29711884753901563,
|
| 708 |
+
"grad_norm": 10.149928390127263,
|
| 709 |
+
"learning_rate": 8.867751527341962e-06,
|
| 710 |
+
"loss": 2.0095,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.30012004801920766,
|
| 715 |
+
"grad_norm": 8.46959243433518,
|
| 716 |
+
"learning_rate": 8.834335362607578e-06,
|
| 717 |
+
"loss": 1.8346,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.30012004801920766,
|
| 722 |
+
"eval_loss": 1.8436174392700195,
|
| 723 |
+
"eval_runtime": 70.088,
|
| 724 |
+
"eval_samples_per_second": 21.131,
|
| 725 |
+
"eval_steps_per_second": 10.572,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.30312124849939975,
|
| 730 |
+
"grad_norm": 16.868801651903272,
|
| 731 |
+
"learning_rate": 8.80049815859821e-06,
|
| 732 |
+
"loss": 1.9479,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.30612244897959184,
|
| 737 |
+
"grad_norm": 10.50023341524374,
|
| 738 |
+
"learning_rate": 8.766243630897002e-06,
|
| 739 |
+
"loss": 2.1128,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.30912364945978393,
|
| 744 |
+
"grad_norm": 8.928156526275373,
|
| 745 |
+
"learning_rate": 8.731575540912422e-06,
|
| 746 |
+
"loss": 1.9959,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.31212484993997597,
|
| 751 |
+
"grad_norm": 11.834343384295739,
|
| 752 |
+
"learning_rate": 8.696497695465237e-06,
|
| 753 |
+
"loss": 1.8446,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.31512605042016806,
|
| 758 |
+
"grad_norm": 14.438889863331674,
|
| 759 |
+
"learning_rate": 8.66101394637048e-06,
|
| 760 |
+
"loss": 1.9538,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.31812725090036015,
|
| 765 |
+
"grad_norm": 7.0509264901284405,
|
| 766 |
+
"learning_rate": 8.625128190014513e-06,
|
| 767 |
+
"loss": 2.224,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.32112845138055224,
|
| 772 |
+
"grad_norm": 10.882784743186303,
|
| 773 |
+
"learning_rate": 8.588844366927156e-06,
|
| 774 |
+
"loss": 1.9669,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3241296518607443,
|
| 779 |
+
"grad_norm": 8.990237158612308,
|
| 780 |
+
"learning_rate": 8.552166461348991e-06,
|
| 781 |
+
"loss": 1.7175,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.32713085234093636,
|
| 786 |
+
"grad_norm": 14.10485370212862,
|
| 787 |
+
"learning_rate": 8.515098500793868e-06,
|
| 788 |
+
"loss": 1.9135,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.33013205282112845,
|
| 793 |
+
"grad_norm": 11.4270403766335,
|
| 794 |
+
"learning_rate": 8.477644555606647e-06,
|
| 795 |
+
"loss": 1.9181,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.33313325330132054,
|
| 800 |
+
"grad_norm": 10.98863933462178,
|
| 801 |
+
"learning_rate": 8.439808738516248e-06,
|
| 802 |
+
"loss": 2.0249,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.33613445378151263,
|
| 807 |
+
"grad_norm": 21.402837855150903,
|
| 808 |
+
"learning_rate": 8.401595204184035e-06,
|
| 809 |
+
"loss": 1.7287,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.33913565426170467,
|
| 814 |
+
"grad_norm": 13.977226200369794,
|
| 815 |
+
"learning_rate": 8.363008148747606e-06,
|
| 816 |
+
"loss": 1.7275,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.34213685474189676,
|
| 821 |
+
"grad_norm": 12.329315260812974,
|
| 822 |
+
"learning_rate": 8.324051809360037e-06,
|
| 823 |
+
"loss": 1.9854,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.34513805522208885,
|
| 828 |
+
"grad_norm": 6.8949526667461125,
|
| 829 |
+
"learning_rate": 8.284730463724585e-06,
|
| 830 |
+
"loss": 1.8173,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.34813925570228094,
|
| 835 |
+
"grad_norm": 15.132137249007318,
|
| 836 |
+
"learning_rate": 8.245048429624983e-06,
|
| 837 |
+
"loss": 2.0162,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.35114045618247297,
|
| 842 |
+
"grad_norm": 11.463625138426867,
|
| 843 |
+
"learning_rate": 8.205010064451314e-06,
|
| 844 |
+
"loss": 2.2115,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.35414165666266506,
|
| 849 |
+
"grad_norm": 12.725809570070531,
|
| 850 |
+
"learning_rate": 8.164619764721523e-06,
|
| 851 |
+
"loss": 2.204,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.35714285714285715,
|
| 856 |
+
"grad_norm": 12.730243560834372,
|
| 857 |
+
"learning_rate": 8.12388196559866e-06,
|
| 858 |
+
"loss": 1.897,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.36014405762304924,
|
| 863 |
+
"grad_norm": 7.029827177766862,
|
| 864 |
+
"learning_rate": 8.082801140403857e-06,
|
| 865 |
+
"loss": 1.7744,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.3631452581032413,
|
| 870 |
+
"grad_norm": 10.414460517503901,
|
| 871 |
+
"learning_rate": 8.041381800125129e-06,
|
| 872 |
+
"loss": 1.8452,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.36614645858343337,
|
| 877 |
+
"grad_norm": 13.745072092763401,
|
| 878 |
+
"learning_rate": 7.999628492922022e-06,
|
| 879 |
+
"loss": 2.0646,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.36914765906362546,
|
| 884 |
+
"grad_norm": 8.775551099349842,
|
| 885 |
+
"learning_rate": 7.957545803626208e-06,
|
| 886 |
+
"loss": 1.9013,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.37214885954381755,
|
| 891 |
+
"grad_norm": 12.599490709310933,
|
| 892 |
+
"learning_rate": 7.915138353238018e-06,
|
| 893 |
+
"loss": 2.0367,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.3751500600240096,
|
| 898 |
+
"grad_norm": 6.256535396667515,
|
| 899 |
+
"learning_rate": 7.872410798419033e-06,
|
| 900 |
+
"loss": 1.9974,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.37815126050420167,
|
| 905 |
+
"grad_norm": 9.33884703529061,
|
| 906 |
+
"learning_rate": 7.829367830980739e-06,
|
| 907 |
+
"loss": 1.9962,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.38115246098439376,
|
| 912 |
+
"grad_norm": 21.706114177368843,
|
| 913 |
+
"learning_rate": 7.786014177369336e-06,
|
| 914 |
+
"loss": 1.9969,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.38415366146458585,
|
| 919 |
+
"grad_norm": 12.19292284047377,
|
| 920 |
+
"learning_rate": 7.742354598146737e-06,
|
| 921 |
+
"loss": 2.0981,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3871548619447779,
|
| 926 |
+
"grad_norm": 9.306186302055167,
|
| 927 |
+
"learning_rate": 7.698393887467822e-06,
|
| 928 |
+
"loss": 1.9351,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.39015606242497,
|
| 933 |
+
"grad_norm": 7.075234259359012,
|
| 934 |
+
"learning_rate": 7.654136872553994e-06,
|
| 935 |
+
"loss": 2.0849,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.39315726290516206,
|
| 940 |
+
"grad_norm": 13.098710223009212,
|
| 941 |
+
"learning_rate": 7.609588413163133e-06,
|
| 942 |
+
"loss": 2.1268,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.39615846338535415,
|
| 947 |
+
"grad_norm": 8.116612120897077,
|
| 948 |
+
"learning_rate": 7.564753401055938e-06,
|
| 949 |
+
"loss": 2.1511,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.39915966386554624,
|
| 954 |
+
"grad_norm": 11.134740327279541,
|
| 955 |
+
"learning_rate": 7.519636759458787e-06,
|
| 956 |
+
"loss": 1.8251,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4021608643457383,
|
| 961 |
+
"grad_norm": 7.351044801101755,
|
| 962 |
+
"learning_rate": 7.474243442523122e-06,
|
| 963 |
+
"loss": 1.9105,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.40516206482593037,
|
| 968 |
+
"grad_norm": 13.084121400843905,
|
| 969 |
+
"learning_rate": 7.428578434781446e-06,
|
| 970 |
+
"loss": 2.0436,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.40816326530612246,
|
| 975 |
+
"grad_norm": 9.072398206431368,
|
| 976 |
+
"learning_rate": 7.382646750599991e-06,
|
| 977 |
+
"loss": 1.9403,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.41116446578631455,
|
| 982 |
+
"grad_norm": 10.586715140991426,
|
| 983 |
+
"learning_rate": 7.33645343362809e-06,
|
| 984 |
+
"loss": 2.0718,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.4141656662665066,
|
| 989 |
+
"grad_norm": 11.515109253824,
|
| 990 |
+
"learning_rate": 7.290003556244359e-06,
|
| 991 |
+
"loss": 1.8263,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4171668667466987,
|
| 996 |
+
"grad_norm": 11.730876807196703,
|
| 997 |
+
"learning_rate": 7.2433022189997e-06,
|
| 998 |
+
"loss": 1.9503,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.42016806722689076,
|
| 1003 |
+
"grad_norm": 10.550292645454324,
|
| 1004 |
+
"learning_rate": 7.196354550057226e-06,
|
| 1005 |
+
"loss": 1.8239,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.42316926770708285,
|
| 1010 |
+
"grad_norm": 9.887874814498124,
|
| 1011 |
+
"learning_rate": 7.1491657046291526e-06,
|
| 1012 |
+
"loss": 1.9299,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4261704681872749,
|
| 1017 |
+
"grad_norm": 12.616008529269662,
|
| 1018 |
+
"learning_rate": 7.101740864410709e-06,
|
| 1019 |
+
"loss": 2.1525,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.429171668667467,
|
| 1024 |
+
"grad_norm": 8.812376323246953,
|
| 1025 |
+
"learning_rate": 7.05408523701116e-06,
|
| 1026 |
+
"loss": 1.8238,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.43217286914765907,
|
| 1031 |
+
"grad_norm": 8.745128290955817,
|
| 1032 |
+
"learning_rate": 7.006204055381957e-06,
|
| 1033 |
+
"loss": 1.6758,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.43517406962785116,
|
| 1038 |
+
"grad_norm": 6.318402234130335,
|
| 1039 |
+
"learning_rate": 6.958102577242128e-06,
|
| 1040 |
+
"loss": 1.9202,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.4381752701080432,
|
| 1045 |
+
"grad_norm": 7.927574856182854,
|
| 1046 |
+
"learning_rate": 6.909786084500939e-06,
|
| 1047 |
+
"loss": 2.0833,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4411764705882353,
|
| 1052 |
+
"grad_norm": 10.544936971680398,
|
| 1053 |
+
"learning_rate": 6.861259882677902e-06,
|
| 1054 |
+
"loss": 2.002,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.44417767106842737,
|
| 1059 |
+
"grad_norm": 11.619710218418861,
|
| 1060 |
+
"learning_rate": 6.8125293003201806e-06,
|
| 1061 |
+
"loss": 1.7993,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.44717887154861946,
|
| 1066 |
+
"grad_norm": 6.420503958767878,
|
| 1067 |
+
"learning_rate": 6.763599688417487e-06,
|
| 1068 |
+
"loss": 1.8841,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.45018007202881155,
|
| 1073 |
+
"grad_norm": 12.533300979520721,
|
| 1074 |
+
"learning_rate": 6.714476419814492e-06,
|
| 1075 |
+
"loss": 1.9325,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.45018007202881155,
|
| 1080 |
+
"eval_loss": 1.7854255437850952,
|
| 1081 |
+
"eval_runtime": 72.7355,
|
| 1082 |
+
"eval_samples_per_second": 20.361,
|
| 1083 |
+
"eval_steps_per_second": 10.188,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.4531812725090036,
|
| 1088 |
+
"grad_norm": 4.747847172239305,
|
| 1089 |
+
"learning_rate": 6.665164888620848e-06,
|
| 1090 |
+
"loss": 1.6663,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.4561824729891957,
|
| 1095 |
+
"grad_norm": 7.525229479358654,
|
| 1096 |
+
"learning_rate": 6.615670509618879e-06,
|
| 1097 |
+
"loss": 1.6184,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.45918367346938777,
|
| 1102 |
+
"grad_norm": 9.73553436099885,
|
| 1103 |
+
"learning_rate": 6.565998717668992e-06,
|
| 1104 |
+
"loss": 2.0157,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.46218487394957986,
|
| 1109 |
+
"grad_norm": 1.9365788113666345,
|
| 1110 |
+
"learning_rate": 6.516154967112891e-06,
|
| 1111 |
+
"loss": 1.5343,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.4651860744297719,
|
| 1116 |
+
"grad_norm": 13.65674435295188,
|
| 1117 |
+
"learning_rate": 6.466144731174645e-06,
|
| 1118 |
+
"loss": 1.8785,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.468187274909964,
|
| 1123 |
+
"grad_norm": 12.365721091880623,
|
| 1124 |
+
"learning_rate": 6.415973501359687e-06,
|
| 1125 |
+
"loss": 1.7204,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.47118847539015607,
|
| 1130 |
+
"grad_norm": 6.498996459559609,
|
| 1131 |
+
"learning_rate": 6.365646786851809e-06,
|
| 1132 |
+
"loss": 1.9123,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.47418967587034816,
|
| 1137 |
+
"grad_norm": 12.248966426285023,
|
| 1138 |
+
"learning_rate": 6.315170113908204e-06,
|
| 1139 |
+
"loss": 2.0724,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.4771908763505402,
|
| 1144 |
+
"grad_norm": 6.254751069477799,
|
| 1145 |
+
"learning_rate": 6.264549025252652e-06,
|
| 1146 |
+
"loss": 2.0417,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4801920768307323,
|
| 1151 |
+
"grad_norm": 11.586505827936087,
|
| 1152 |
+
"learning_rate": 6.213789079466873e-06,
|
| 1153 |
+
"loss": 1.9998,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4831932773109244,
|
| 1158 |
+
"grad_norm": 11.628169667737911,
|
| 1159 |
+
"learning_rate": 6.1628958503801635e-06,
|
| 1160 |
+
"loss": 1.9805,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.48619447779111646,
|
| 1165 |
+
"grad_norm": 10.266695075168396,
|
| 1166 |
+
"learning_rate": 6.111874926457344e-06,
|
| 1167 |
+
"loss": 1.9866,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.4891956782713085,
|
| 1172 |
+
"grad_norm": 7.864602445607685,
|
| 1173 |
+
"learning_rate": 6.0607319101850955e-06,
|
| 1174 |
+
"loss": 2.0325,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4921968787515006,
|
| 1179 |
+
"grad_norm": 7.852131699169073,
|
| 1180 |
+
"learning_rate": 6.009472417456779e-06,
|
| 1181 |
+
"loss": 2.136,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4951980792316927,
|
| 1186 |
+
"grad_norm": 9.171127473935298,
|
| 1187 |
+
"learning_rate": 5.958102076955753e-06,
|
| 1188 |
+
"loss": 1.8371,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.49819927971188477,
|
| 1193 |
+
"grad_norm": 13.155484650564988,
|
| 1194 |
+
"learning_rate": 5.906626529537311e-06,
|
| 1195 |
+
"loss": 2.1112,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.5012004801920769,
|
| 1200 |
+
"grad_norm": 14.407405269785295,
|
| 1201 |
+
"learning_rate": 5.855051427609265e-06,
|
| 1202 |
+
"loss": 2.1317,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.5042016806722689,
|
| 1207 |
+
"grad_norm": 7.944398594556855,
|
| 1208 |
+
"learning_rate": 5.803382434511274e-06,
|
| 1209 |
+
"loss": 1.9131,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.507202881152461,
|
| 1214 |
+
"grad_norm": 12.067931060345453,
|
| 1215 |
+
"learning_rate": 5.751625223892964e-06,
|
| 1216 |
+
"loss": 1.961,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.5102040816326531,
|
| 1221 |
+
"grad_norm": 11.305421590297874,
|
| 1222 |
+
"learning_rate": 5.699785479090917e-06,
|
| 1223 |
+
"loss": 1.8233,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.5132052821128451,
|
| 1228 |
+
"grad_norm": 10.568805120830348,
|
| 1229 |
+
"learning_rate": 5.647868892504597e-06,
|
| 1230 |
+
"loss": 1.8034,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.5162064825930373,
|
| 1235 |
+
"grad_norm": 8.901920906884708,
|
| 1236 |
+
"learning_rate": 5.595881164971284e-06,
|
| 1237 |
+
"loss": 2.1088,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.5192076830732293,
|
| 1242 |
+
"grad_norm": 10.818151872015115,
|
| 1243 |
+
"learning_rate": 5.543828005140076e-06,
|
| 1244 |
+
"loss": 1.9505,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.5222088835534213,
|
| 1249 |
+
"grad_norm": 19.0269528128246,
|
| 1250 |
+
"learning_rate": 5.491715128845037e-06,
|
| 1251 |
+
"loss": 2.1158,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.5252100840336135,
|
| 1256 |
+
"grad_norm": 6.368156672789348,
|
| 1257 |
+
"learning_rate": 5.439548258477549e-06,
|
| 1258 |
+
"loss": 1.526,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.5282112845138055,
|
| 1263 |
+
"grad_norm": 14.33226946197169,
|
| 1264 |
+
"learning_rate": 5.387333122357966e-06,
|
| 1265 |
+
"loss": 1.9441,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5312124849939976,
|
| 1270 |
+
"grad_norm": 10.893640588904004,
|
| 1271 |
+
"learning_rate": 5.3350754541065805e-06,
|
| 1272 |
+
"loss": 1.5771,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5342136854741897,
|
| 1277 |
+
"grad_norm": 11.613038829759443,
|
| 1278 |
+
"learning_rate": 5.282780992014043e-06,
|
| 1279 |
+
"loss": 1.8335,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.5372148859543817,
|
| 1284 |
+
"grad_norm": 6.446614047723568,
|
| 1285 |
+
"learning_rate": 5.230455478411243e-06,
|
| 1286 |
+
"loss": 1.9638,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5402160864345739,
|
| 1291 |
+
"grad_norm": 14.258595482993,
|
| 1292 |
+
"learning_rate": 5.1781046590387675e-06,
|
| 1293 |
+
"loss": 1.8887,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.5432172869147659,
|
| 1298 |
+
"grad_norm": 10.102795668494593,
|
| 1299 |
+
"learning_rate": 5.125734282415967e-06,
|
| 1300 |
+
"loss": 2.1767,
|
| 1301 |
+
"step": 1810
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5462184873949579,
|
| 1305 |
+
"grad_norm": 11.29991368417218,
|
| 1306 |
+
"learning_rate": 5.0733500992097295e-06,
|
| 1307 |
+
"loss": 1.8136,
|
| 1308 |
+
"step": 1820
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.5492196878751501,
|
| 1312 |
+
"grad_norm": 5.146344981754679,
|
| 1313 |
+
"learning_rate": 5.020957861603011e-06,
|
| 1314 |
+
"loss": 1.6411,
|
| 1315 |
+
"step": 1830
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5522208883553421,
|
| 1319 |
+
"grad_norm": 14.066643454727922,
|
| 1320 |
+
"learning_rate": 4.9685633226632004e-06,
|
| 1321 |
+
"loss": 1.8657,
|
| 1322 |
+
"step": 1840
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5552220888355343,
|
| 1326 |
+
"grad_norm": 9.885151028744932,
|
| 1327 |
+
"learning_rate": 4.916172235710393e-06,
|
| 1328 |
+
"loss": 1.8143,
|
| 1329 |
+
"step": 1850
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5582232893157263,
|
| 1333 |
+
"grad_norm": 11.550762892952077,
|
| 1334 |
+
"learning_rate": 4.8637903536856266e-06,
|
| 1335 |
+
"loss": 1.9513,
|
| 1336 |
+
"step": 1860
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5612244897959183,
|
| 1340 |
+
"grad_norm": 16.261531223174785,
|
| 1341 |
+
"learning_rate": 4.811423428519169e-06,
|
| 1342 |
+
"loss": 1.6205,
|
| 1343 |
+
"step": 1870
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5642256902761105,
|
| 1347 |
+
"grad_norm": 11.38322225643573,
|
| 1348 |
+
"learning_rate": 4.759077210498913e-06,
|
| 1349 |
+
"loss": 1.7196,
|
| 1350 |
+
"step": 1880
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5672268907563025,
|
| 1354 |
+
"grad_norm": 8.776094085092314,
|
| 1355 |
+
"learning_rate": 4.706757447638945e-06,
|
| 1356 |
+
"loss": 2.0409,
|
| 1357 |
+
"step": 1890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5702280912364946,
|
| 1361 |
+
"grad_norm": 9.049484315692625,
|
| 1362 |
+
"learning_rate": 4.654469885048376e-06,
|
| 1363 |
+
"loss": 1.9866,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.5732292917166867,
|
| 1368 |
+
"grad_norm": 10.657785810994662,
|
| 1369 |
+
"learning_rate": 4.602220264300481e-06,
|
| 1370 |
+
"loss": 1.8922,
|
| 1371 |
+
"step": 1910
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5762304921968787,
|
| 1375 |
+
"grad_norm": 9.342865110666766,
|
| 1376 |
+
"learning_rate": 4.55001432280223e-06,
|
| 1377 |
+
"loss": 1.7542,
|
| 1378 |
+
"step": 1920
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5792316926770709,
|
| 1382 |
+
"grad_norm": 12.081799903070168,
|
| 1383 |
+
"learning_rate": 4.497857793164277e-06,
|
| 1384 |
+
"loss": 1.9913,
|
| 1385 |
+
"step": 1930
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5822328931572629,
|
| 1389 |
+
"grad_norm": 7.619917781656242,
|
| 1390 |
+
"learning_rate": 4.445756402571483e-06,
|
| 1391 |
+
"loss": 1.9881,
|
| 1392 |
+
"step": 1940
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5852340936374549,
|
| 1396 |
+
"grad_norm": 9.093969376778242,
|
| 1397 |
+
"learning_rate": 4.393715872154014e-06,
|
| 1398 |
+
"loss": 1.7711,
|
| 1399 |
+
"step": 1950
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5882352941176471,
|
| 1403 |
+
"grad_norm": 9.108154177538303,
|
| 1404 |
+
"learning_rate": 4.3417419163591296e-06,
|
| 1405 |
+
"loss": 1.7914,
|
| 1406 |
+
"step": 1960
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5912364945978391,
|
| 1410 |
+
"grad_norm": 9.864863366342805,
|
| 1411 |
+
"learning_rate": 4.2898402423236835e-06,
|
| 1412 |
+
"loss": 1.7734,
|
| 1413 |
+
"step": 1970
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5942376950780313,
|
| 1417 |
+
"grad_norm": 14.65031277951791,
|
| 1418 |
+
"learning_rate": 4.238016549247443e-06,
|
| 1419 |
+
"loss": 1.8682,
|
| 1420 |
+
"step": 1980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.5972388955582233,
|
| 1424 |
+
"grad_norm": 15.195046706414468,
|
| 1425 |
+
"learning_rate": 4.186276527767273e-06,
|
| 1426 |
+
"loss": 1.8358,
|
| 1427 |
+
"step": 1990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.6002400960384153,
|
| 1431 |
+
"grad_norm": 7.420521707718542,
|
| 1432 |
+
"learning_rate": 4.1346258593322555e-06,
|
| 1433 |
+
"loss": 1.8923,
|
| 1434 |
+
"step": 2000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.6002400960384153,
|
| 1438 |
+
"eval_loss": 1.7435638904571533,
|
| 1439 |
+
"eval_runtime": 69.2816,
|
| 1440 |
+
"eval_samples_per_second": 21.377,
|
| 1441 |
+
"eval_steps_per_second": 10.695,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.6032412965186075,
|
| 1446 |
+
"grad_norm": 25.45598758249549,
|
| 1447 |
+
"learning_rate": 4.08307021557983e-06,
|
| 1448 |
+
"loss": 1.7191,
|
| 1449 |
+
"step": 2010
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.6062424969987995,
|
| 1453 |
+
"grad_norm": 7.897349852896533,
|
| 1454 |
+
"learning_rate": 4.031615257712996e-06,
|
| 1455 |
+
"loss": 1.9881,
|
| 1456 |
+
"step": 2020
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.6092436974789915,
|
| 1460 |
+
"grad_norm": 6.16625120190022,
|
| 1461 |
+
"learning_rate": 3.98026663587868e-06,
|
| 1462 |
+
"loss": 1.7836,
|
| 1463 |
+
"step": 2030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.6122448979591837,
|
| 1467 |
+
"grad_norm": 20.615497493186695,
|
| 1468 |
+
"learning_rate": 3.929029988547296e-06,
|
| 1469 |
+
"loss": 1.9693,
|
| 1470 |
+
"step": 2040
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.6152460984393757,
|
| 1474 |
+
"grad_norm": 16.331083465757896,
|
| 1475 |
+
"learning_rate": 3.8779109418936074e-06,
|
| 1476 |
+
"loss": 1.9877,
|
| 1477 |
+
"step": 2050
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.6182472989195679,
|
| 1481 |
+
"grad_norm": 8.975255093028004,
|
| 1482 |
+
"learning_rate": 3.826915109178925e-06,
|
| 1483 |
+
"loss": 1.7951,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.6212484993997599,
|
| 1488 |
+
"grad_norm": 14.614156710342609,
|
| 1489 |
+
"learning_rate": 3.776048090134726e-06,
|
| 1490 |
+
"loss": 2.0532,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.6242496998799519,
|
| 1495 |
+
"grad_norm": 14.227607937991625,
|
| 1496 |
+
"learning_rate": 3.725315470347769e-06,
|
| 1497 |
+
"loss": 1.6202,
|
| 1498 |
+
"step": 2080
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.6272509003601441,
|
| 1502 |
+
"grad_norm": 9.755464711787543,
|
| 1503 |
+
"learning_rate": 3.6747228206467435e-06,
|
| 1504 |
+
"loss": 1.8552,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.6302521008403361,
|
| 1509 |
+
"grad_norm": 11.720295448594253,
|
| 1510 |
+
"learning_rate": 3.62427569649056e-06,
|
| 1511 |
+
"loss": 2.0746,
|
| 1512 |
+
"step": 2100
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.6332533013205283,
|
| 1516 |
+
"grad_norm": 12.420750898009793,
|
| 1517 |
+
"learning_rate": 3.5739796373583124e-06,
|
| 1518 |
+
"loss": 1.9033,
|
| 1519 |
+
"step": 2110
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.6362545018007203,
|
| 1523 |
+
"grad_norm": 18.15546870310451,
|
| 1524 |
+
"learning_rate": 3.5238401661410016e-06,
|
| 1525 |
+
"loss": 1.949,
|
| 1526 |
+
"step": 2120
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.6392557022809123,
|
| 1530 |
+
"grad_norm": 8.838596253346461,
|
| 1531 |
+
"learning_rate": 3.473862788535083e-06,
|
| 1532 |
+
"loss": 1.9731,
|
| 1533 |
+
"step": 2130
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.6422569027611045,
|
| 1537 |
+
"grad_norm": 7.021128179443776,
|
| 1538 |
+
"learning_rate": 3.4240529924378933e-06,
|
| 1539 |
+
"loss": 1.6426,
|
| 1540 |
+
"step": 2140
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.6452581032412965,
|
| 1544 |
+
"grad_norm": 16.281499993295807,
|
| 1545 |
+
"learning_rate": 3.3744162473450435e-06,
|
| 1546 |
+
"loss": 1.7679,
|
| 1547 |
+
"step": 2150
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.6482593037214885,
|
| 1551 |
+
"grad_norm": 8.482637058307281,
|
| 1552 |
+
"learning_rate": 3.3249580037498263e-06,
|
| 1553 |
+
"loss": 1.9333,
|
| 1554 |
+
"step": 2160
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.6512605042016807,
|
| 1558 |
+
"grad_norm": 5.789850691609375,
|
| 1559 |
+
"learning_rate": 3.2756836925447044e-06,
|
| 1560 |
+
"loss": 1.9397,
|
| 1561 |
+
"step": 2170
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.6542617046818727,
|
| 1565 |
+
"grad_norm": 11.068102019401588,
|
| 1566 |
+
"learning_rate": 3.226598724424961e-06,
|
| 1567 |
+
"loss": 1.7214,
|
| 1568 |
+
"step": 2180
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.6572629051620649,
|
| 1572 |
+
"grad_norm": 9.416049920187813,
|
| 1573 |
+
"learning_rate": 3.177708489294567e-06,
|
| 1574 |
+
"loss": 1.9513,
|
| 1575 |
+
"step": 2190
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.6602641056422569,
|
| 1579 |
+
"grad_norm": 10.76548308072494,
|
| 1580 |
+
"learning_rate": 3.1290183556743215e-06,
|
| 1581 |
+
"loss": 1.8658,
|
| 1582 |
+
"step": 2200
|
| 1583 |
+
}
|
| 1584 |
+
],
|
| 1585 |
+
"logging_steps": 10,
|
| 1586 |
+
"max_steps": 3332,
|
| 1587 |
+
"num_input_tokens_seen": 0,
|
| 1588 |
+
"num_train_epochs": 1,
|
| 1589 |
+
"save_steps": 100,
|
| 1590 |
+
"stateful_callbacks": {
|
| 1591 |
+
"TrainerControl": {
|
| 1592 |
+
"args": {
|
| 1593 |
+
"should_epoch_stop": false,
|
| 1594 |
+
"should_evaluate": false,
|
| 1595 |
+
"should_log": false,
|
| 1596 |
+
"should_save": true,
|
| 1597 |
+
"should_training_stop": false
|
| 1598 |
+
},
|
| 1599 |
+
"attributes": {}
|
| 1600 |
+
}
|
| 1601 |
+
},
|
| 1602 |
+
"total_flos": 2536491909120.0,
|
| 1603 |
+
"train_batch_size": 2,
|
| 1604 |
+
"trial_name": null,
|
| 1605 |
+
"trial_params": null
|
| 1606 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2900/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|
checkpoint-2900/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-2900/tokenizer_config.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 186 |
+
"pad_token": "<|pad|>",
|
| 187 |
+
"padding_side": "right",
|
| 188 |
+
"split_special_tokens": false,
|
| 189 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 190 |
+
"unk_token": "<|endoftext|>"
|
| 191 |
+
}
|
checkpoint-2900/trainer_state.json
ADDED
|
@@ -0,0 +1,2104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8703481392557023,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.003001200480192077,
|
| 14 |
+
"grad_norm": 16.322778038786794,
|
| 15 |
+
"learning_rate": 2.694610778443114e-07,
|
| 16 |
+
"loss": 2.4961,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.006002400960384154,
|
| 21 |
+
"grad_norm": 21.26487128326307,
|
| 22 |
+
"learning_rate": 5.688622754491019e-07,
|
| 23 |
+
"loss": 2.4545,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00900360144057623,
|
| 28 |
+
"grad_norm": 20.493921349321404,
|
| 29 |
+
"learning_rate": 8.682634730538923e-07,
|
| 30 |
+
"loss": 2.4459,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.012004801920768308,
|
| 35 |
+
"grad_norm": 16.939655978226025,
|
| 36 |
+
"learning_rate": 1.1676646706586827e-06,
|
| 37 |
+
"loss": 2.4742,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.015006002400960384,
|
| 42 |
+
"grad_norm": 23.865531522300767,
|
| 43 |
+
"learning_rate": 1.4670658682634732e-06,
|
| 44 |
+
"loss": 2.0074,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01800720288115246,
|
| 49 |
+
"grad_norm": 16.606288718277256,
|
| 50 |
+
"learning_rate": 1.7664670658682636e-06,
|
| 51 |
+
"loss": 1.7784,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02100840336134454,
|
| 56 |
+
"grad_norm": 14.41517087399792,
|
| 57 |
+
"learning_rate": 2.065868263473054e-06,
|
| 58 |
+
"loss": 2.1435,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.024009603841536616,
|
| 63 |
+
"grad_norm": 9.610371534852842,
|
| 64 |
+
"learning_rate": 2.3652694610778446e-06,
|
| 65 |
+
"loss": 1.8848,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02701080432172869,
|
| 70 |
+
"grad_norm": 11.723596844563824,
|
| 71 |
+
"learning_rate": 2.664670658682635e-06,
|
| 72 |
+
"loss": 2.2553,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.030012004801920768,
|
| 77 |
+
"grad_norm": 28.025837302158916,
|
| 78 |
+
"learning_rate": 2.9640718562874255e-06,
|
| 79 |
+
"loss": 1.9136,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.033013205282112844,
|
| 84 |
+
"grad_norm": 9.44674022586452,
|
| 85 |
+
"learning_rate": 3.263473053892216e-06,
|
| 86 |
+
"loss": 2.1588,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03601440576230492,
|
| 91 |
+
"grad_norm": 12.826206690198743,
|
| 92 |
+
"learning_rate": 3.562874251497006e-06,
|
| 93 |
+
"loss": 1.9439,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.039015606242496996,
|
| 98 |
+
"grad_norm": 13.332854551269488,
|
| 99 |
+
"learning_rate": 3.862275449101797e-06,
|
| 100 |
+
"loss": 1.9872,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.04201680672268908,
|
| 105 |
+
"grad_norm": 13.687005134844258,
|
| 106 |
+
"learning_rate": 4.161676646706587e-06,
|
| 107 |
+
"loss": 2.018,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.045018007202881155,
|
| 112 |
+
"grad_norm": 11.10704695361387,
|
| 113 |
+
"learning_rate": 4.461077844311378e-06,
|
| 114 |
+
"loss": 1.8614,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.04801920768307323,
|
| 119 |
+
"grad_norm": 18.355044203461766,
|
| 120 |
+
"learning_rate": 4.760479041916168e-06,
|
| 121 |
+
"loss": 1.961,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.05102040816326531,
|
| 126 |
+
"grad_norm": 15.09389345242339,
|
| 127 |
+
"learning_rate": 5.059880239520959e-06,
|
| 128 |
+
"loss": 2.21,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.05402160864345738,
|
| 133 |
+
"grad_norm": 10.156004340051048,
|
| 134 |
+
"learning_rate": 5.359281437125749e-06,
|
| 135 |
+
"loss": 2.1261,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05702280912364946,
|
| 140 |
+
"grad_norm": 15.345968230792714,
|
| 141 |
+
"learning_rate": 5.658682634730539e-06,
|
| 142 |
+
"loss": 2.0072,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.060024009603841535,
|
| 147 |
+
"grad_norm": 11.153556976885293,
|
| 148 |
+
"learning_rate": 5.95808383233533e-06,
|
| 149 |
+
"loss": 1.9935,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.06302521008403361,
|
| 154 |
+
"grad_norm": 9.491849063073436,
|
| 155 |
+
"learning_rate": 6.25748502994012e-06,
|
| 156 |
+
"loss": 1.6912,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.06602641056422569,
|
| 161 |
+
"grad_norm": 9.775572755148744,
|
| 162 |
+
"learning_rate": 6.556886227544911e-06,
|
| 163 |
+
"loss": 2.2844,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06902761104441776,
|
| 168 |
+
"grad_norm": 10.444304091533951,
|
| 169 |
+
"learning_rate": 6.8562874251497016e-06,
|
| 170 |
+
"loss": 1.9957,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.07202881152460984,
|
| 175 |
+
"grad_norm": 12.315712653283379,
|
| 176 |
+
"learning_rate": 7.155688622754492e-06,
|
| 177 |
+
"loss": 1.718,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.07503001200480192,
|
| 182 |
+
"grad_norm": 15.4266884794421,
|
| 183 |
+
"learning_rate": 7.4550898203592825e-06,
|
| 184 |
+
"loss": 1.8986,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07803121248499399,
|
| 189 |
+
"grad_norm": 15.350622303641131,
|
| 190 |
+
"learning_rate": 7.754491017964072e-06,
|
| 191 |
+
"loss": 2.1906,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.08103241296518607,
|
| 196 |
+
"grad_norm": 10.100826281853637,
|
| 197 |
+
"learning_rate": 8.053892215568863e-06,
|
| 198 |
+
"loss": 2.062,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08403361344537816,
|
| 203 |
+
"grad_norm": 9.985084559589948,
|
| 204 |
+
"learning_rate": 8.353293413173653e-06,
|
| 205 |
+
"loss": 2.0219,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08703481392557023,
|
| 210 |
+
"grad_norm": 25.52843769465498,
|
| 211 |
+
"learning_rate": 8.652694610778444e-06,
|
| 212 |
+
"loss": 1.774,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.09003601440576231,
|
| 217 |
+
"grad_norm": 7.010526730435224,
|
| 218 |
+
"learning_rate": 8.952095808383234e-06,
|
| 219 |
+
"loss": 1.7647,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.09303721488595439,
|
| 224 |
+
"grad_norm": 10.925177037546252,
|
| 225 |
+
"learning_rate": 9.251497005988024e-06,
|
| 226 |
+
"loss": 1.853,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.09603841536614646,
|
| 231 |
+
"grad_norm": 13.12192108271367,
|
| 232 |
+
"learning_rate": 9.550898203592815e-06,
|
| 233 |
+
"loss": 2.023,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09903961584633854,
|
| 238 |
+
"grad_norm": 19.146417141785633,
|
| 239 |
+
"learning_rate": 9.850299401197606e-06,
|
| 240 |
+
"loss": 1.8804,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.10204081632653061,
|
| 245 |
+
"grad_norm": 17.095401175842863,
|
| 246 |
+
"learning_rate": 9.99993136976086e-06,
|
| 247 |
+
"loss": 2.0625,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.10504201680672269,
|
| 252 |
+
"grad_norm": 14.915026178785793,
|
| 253 |
+
"learning_rate": 9.99938233915195e-06,
|
| 254 |
+
"loss": 1.7554,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.10804321728691477,
|
| 259 |
+
"grad_norm": 12.3557938764668,
|
| 260 |
+
"learning_rate": 9.99828433822188e-06,
|
| 261 |
+
"loss": 1.8197,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.11104441776710684,
|
| 266 |
+
"grad_norm": 16.732139399887032,
|
| 267 |
+
"learning_rate": 9.996637487539526e-06,
|
| 268 |
+
"loss": 1.9554,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.11404561824729892,
|
| 273 |
+
"grad_norm": 9.472954878862216,
|
| 274 |
+
"learning_rate": 9.99444196794166e-06,
|
| 275 |
+
"loss": 1.8419,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.117046818727491,
|
| 280 |
+
"grad_norm": 14.45943322716144,
|
| 281 |
+
"learning_rate": 9.99169802051308e-06,
|
| 282 |
+
"loss": 1.9554,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.12004801920768307,
|
| 287 |
+
"grad_norm": 11.816006243448049,
|
| 288 |
+
"learning_rate": 9.988405946560151e-06,
|
| 289 |
+
"loss": 1.6209,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12304921968787515,
|
| 294 |
+
"grad_norm": 19.870456146468612,
|
| 295 |
+
"learning_rate": 9.984566107577707e-06,
|
| 296 |
+
"loss": 2.1652,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.12605042016806722,
|
| 301 |
+
"grad_norm": 15.008106738503946,
|
| 302 |
+
"learning_rate": 9.980178925209363e-06,
|
| 303 |
+
"loss": 1.6964,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1290516206482593,
|
| 308 |
+
"grad_norm": 17.195341077337165,
|
| 309 |
+
"learning_rate": 9.975244881201209e-06,
|
| 310 |
+
"loss": 1.861,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.13205282112845138,
|
| 315 |
+
"grad_norm": 12.45396867483932,
|
| 316 |
+
"learning_rate": 9.969764517348924e-06,
|
| 317 |
+
"loss": 1.7937,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.13505402160864347,
|
| 322 |
+
"grad_norm": 9.707765043650019,
|
| 323 |
+
"learning_rate": 9.963738435438267e-06,
|
| 324 |
+
"loss": 1.956,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.13805522208883553,
|
| 329 |
+
"grad_norm": 12.149984169068404,
|
| 330 |
+
"learning_rate": 9.957167297179004e-06,
|
| 331 |
+
"loss": 1.9112,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.14105642256902762,
|
| 336 |
+
"grad_norm": 11.64329798977207,
|
| 337 |
+
"learning_rate": 9.950051824132247e-06,
|
| 338 |
+
"loss": 2.1092,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.14405762304921968,
|
| 343 |
+
"grad_norm": 13.559828016858319,
|
| 344 |
+
"learning_rate": 9.942392797631222e-06,
|
| 345 |
+
"loss": 2.0729,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14705882352941177,
|
| 350 |
+
"grad_norm": 15.255784576157163,
|
| 351 |
+
"learning_rate": 9.934191058695467e-06,
|
| 352 |
+
"loss": 1.9601,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.15006002400960383,
|
| 357 |
+
"grad_norm": 15.12208631421886,
|
| 358 |
+
"learning_rate": 9.925447507938493e-06,
|
| 359 |
+
"loss": 1.8079,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.15006002400960383,
|
| 364 |
+
"eval_loss": 1.8881598711013794,
|
| 365 |
+
"eval_runtime": 71.4162,
|
| 366 |
+
"eval_samples_per_second": 20.738,
|
| 367 |
+
"eval_steps_per_second": 10.376,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.15306122448979592,
|
| 372 |
+
"grad_norm": 9.812255338971053,
|
| 373 |
+
"learning_rate": 9.916163105468872e-06,
|
| 374 |
+
"loss": 1.9261,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.15606242496998798,
|
| 379 |
+
"grad_norm": 16.56967240161569,
|
| 380 |
+
"learning_rate": 9.90633887078483e-06,
|
| 381 |
+
"loss": 2.1224,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.15906362545018007,
|
| 386 |
+
"grad_norm": 10.921999649807898,
|
| 387 |
+
"learning_rate": 9.895975882662283e-06,
|
| 388 |
+
"loss": 1.7545,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.16206482593037214,
|
| 393 |
+
"grad_norm": 11.686083276616063,
|
| 394 |
+
"learning_rate": 9.885075279036385e-06,
|
| 395 |
+
"loss": 2.0052,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.16506602641056423,
|
| 400 |
+
"grad_norm": 13.670316963331478,
|
| 401 |
+
"learning_rate": 9.873638256876577e-06,
|
| 402 |
+
"loss": 1.8232,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.16806722689075632,
|
| 407 |
+
"grad_norm": 10.550976781841975,
|
| 408 |
+
"learning_rate": 9.861666072055144e-06,
|
| 409 |
+
"loss": 2.0087,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.17106842737094838,
|
| 414 |
+
"grad_norm": 7.518022216683535,
|
| 415 |
+
"learning_rate": 9.849160039209317e-06,
|
| 416 |
+
"loss": 2.0186,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.17406962785114047,
|
| 421 |
+
"grad_norm": 18.610725609857187,
|
| 422 |
+
"learning_rate": 9.83612153159691e-06,
|
| 423 |
+
"loss": 1.9651,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.17707082833133253,
|
| 428 |
+
"grad_norm": 14.468204525410128,
|
| 429 |
+
"learning_rate": 9.822551980945526e-06,
|
| 430 |
+
"loss": 1.8678,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.18007202881152462,
|
| 435 |
+
"grad_norm": 10.68638583134911,
|
| 436 |
+
"learning_rate": 9.808452877295356e-06,
|
| 437 |
+
"loss": 2.1099,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.18307322929171668,
|
| 442 |
+
"grad_norm": 6.8000928033318555,
|
| 443 |
+
"learning_rate": 9.79382576883554e-06,
|
| 444 |
+
"loss": 2.0071,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.18607442977190877,
|
| 449 |
+
"grad_norm": 9.517671427003565,
|
| 450 |
+
"learning_rate": 9.778672261734172e-06,
|
| 451 |
+
"loss": 2.2586,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.18907563025210083,
|
| 456 |
+
"grad_norm": 17.30722139026249,
|
| 457 |
+
"learning_rate": 9.762994019961944e-06,
|
| 458 |
+
"loss": 1.9017,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.19207683073229292,
|
| 463 |
+
"grad_norm": 7.832218568217347,
|
| 464 |
+
"learning_rate": 9.746792765109412e-06,
|
| 465 |
+
"loss": 2.0726,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.195078031212485,
|
| 470 |
+
"grad_norm": 15.595751845972346,
|
| 471 |
+
"learning_rate": 9.730070276197955e-06,
|
| 472 |
+
"loss": 2.1412,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.19807923169267708,
|
| 477 |
+
"grad_norm": 14.534725999964142,
|
| 478 |
+
"learning_rate": 9.712828389484432e-06,
|
| 479 |
+
"loss": 2.0257,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.20108043217286914,
|
| 484 |
+
"grad_norm": 9.963604466793788,
|
| 485 |
+
"learning_rate": 9.695068998259547e-06,
|
| 486 |
+
"loss": 1.9898,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.20408163265306123,
|
| 491 |
+
"grad_norm": 12.040002240054593,
|
| 492 |
+
"learning_rate": 9.676794052639937e-06,
|
| 493 |
+
"loss": 2.2448,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.2070828331332533,
|
| 498 |
+
"grad_norm": 15.184552955496128,
|
| 499 |
+
"learning_rate": 9.658005559354053e-06,
|
| 500 |
+
"loss": 1.9303,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.21008403361344538,
|
| 505 |
+
"grad_norm": 10.529109691209351,
|
| 506 |
+
"learning_rate": 9.638705581521798e-06,
|
| 507 |
+
"loss": 1.9958,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.21308523409363744,
|
| 512 |
+
"grad_norm": 11.644168043518746,
|
| 513 |
+
"learning_rate": 9.618896238427973e-06,
|
| 514 |
+
"loss": 1.8387,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.21608643457382953,
|
| 519 |
+
"grad_norm": 10.27332830146538,
|
| 520 |
+
"learning_rate": 9.598579705289579e-06,
|
| 521 |
+
"loss": 1.9449,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.2190876350540216,
|
| 526 |
+
"grad_norm": 5.679908324076684,
|
| 527 |
+
"learning_rate": 9.577758213016948e-06,
|
| 528 |
+
"loss": 2.0876,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.22208883553421369,
|
| 533 |
+
"grad_norm": 12.59216857148061,
|
| 534 |
+
"learning_rate": 9.55643404796878e-06,
|
| 535 |
+
"loss": 1.6231,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.22509003601440578,
|
| 540 |
+
"grad_norm": 11.87232412833194,
|
| 541 |
+
"learning_rate": 9.534609551701078e-06,
|
| 542 |
+
"loss": 1.7406,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.22809123649459784,
|
| 547 |
+
"grad_norm": 11.39859069066619,
|
| 548 |
+
"learning_rate": 9.512287120710032e-06,
|
| 549 |
+
"loss": 2.1341,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.23109243697478993,
|
| 554 |
+
"grad_norm": 9.182462389068496,
|
| 555 |
+
"learning_rate": 9.489469206168863e-06,
|
| 556 |
+
"loss": 1.8263,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.234093637454982,
|
| 561 |
+
"grad_norm": 7.77593574851048,
|
| 562 |
+
"learning_rate": 9.466158313658665e-06,
|
| 563 |
+
"loss": 2.0274,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.23709483793517408,
|
| 568 |
+
"grad_norm": 9.473304898118002,
|
| 569 |
+
"learning_rate": 9.442357002893275e-06,
|
| 570 |
+
"loss": 1.7858,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.24009603841536614,
|
| 575 |
+
"grad_norm": 12.918279823767726,
|
| 576 |
+
"learning_rate": 9.418067887438194e-06,
|
| 577 |
+
"loss": 1.9741,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.24309723889555823,
|
| 582 |
+
"grad_norm": 16.087139659433475,
|
| 583 |
+
"learning_rate": 9.393293634423604e-06,
|
| 584 |
+
"loss": 2.0156,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.2460984393757503,
|
| 589 |
+
"grad_norm": 12.503098107833772,
|
| 590 |
+
"learning_rate": 9.368036964251488e-06,
|
| 591 |
+
"loss": 1.8051,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.24909963985594238,
|
| 596 |
+
"grad_norm": 17.921159341402873,
|
| 597 |
+
"learning_rate": 9.342300650296911e-06,
|
| 598 |
+
"loss": 2.0905,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.25210084033613445,
|
| 603 |
+
"grad_norm": 8.181948558613119,
|
| 604 |
+
"learning_rate": 9.316087518603491e-06,
|
| 605 |
+
"loss": 2.1614,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.25510204081632654,
|
| 610 |
+
"grad_norm": 12.386120651762177,
|
| 611 |
+
"learning_rate": 9.289400447573068e-06,
|
| 612 |
+
"loss": 1.9288,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.2581032412965186,
|
| 617 |
+
"grad_norm": 12.82368671615243,
|
| 618 |
+
"learning_rate": 9.262242367649637e-06,
|
| 619 |
+
"loss": 1.8841,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.26110444177671066,
|
| 624 |
+
"grad_norm": 11.682775075383281,
|
| 625 |
+
"learning_rate": 9.23461626099756e-06,
|
| 626 |
+
"loss": 1.8096,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.26410564225690275,
|
| 631 |
+
"grad_norm": 10.977666012081006,
|
| 632 |
+
"learning_rate": 9.20652516117411e-06,
|
| 633 |
+
"loss": 2.0035,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.26710684273709484,
|
| 638 |
+
"grad_norm": 10.140829194373916,
|
| 639 |
+
"learning_rate": 9.177972152796352e-06,
|
| 640 |
+
"loss": 1.8845,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.27010804321728693,
|
| 645 |
+
"grad_norm": 11.31872075294124,
|
| 646 |
+
"learning_rate": 9.148960371202442e-06,
|
| 647 |
+
"loss": 2.1503,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.27310924369747897,
|
| 652 |
+
"grad_norm": 15.07747778104917,
|
| 653 |
+
"learning_rate": 9.119493002107325e-06,
|
| 654 |
+
"loss": 2.1282,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.27611044417767105,
|
| 659 |
+
"grad_norm": 14.623330843128887,
|
| 660 |
+
"learning_rate": 9.089573281252938e-06,
|
| 661 |
+
"loss": 1.836,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.27911164465786314,
|
| 666 |
+
"grad_norm": 9.349353118072754,
|
| 667 |
+
"learning_rate": 9.059204494052884e-06,
|
| 668 |
+
"loss": 2.0206,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.28211284513805523,
|
| 673 |
+
"grad_norm": 13.132253499401044,
|
| 674 |
+
"learning_rate": 9.028389975231687e-06,
|
| 675 |
+
"loss": 2.0025,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2851140456182473,
|
| 680 |
+
"grad_norm": 8.77966207647504,
|
| 681 |
+
"learning_rate": 8.997133108458594e-06,
|
| 682 |
+
"loss": 2.0201,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.28811524609843936,
|
| 687 |
+
"grad_norm": 7.676366705721278,
|
| 688 |
+
"learning_rate": 8.965437325976036e-06,
|
| 689 |
+
"loss": 1.8401,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.29111644657863145,
|
| 694 |
+
"grad_norm": 17.688333111422782,
|
| 695 |
+
"learning_rate": 8.93330610822274e-06,
|
| 696 |
+
"loss": 1.7173,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.29411764705882354,
|
| 701 |
+
"grad_norm": 10.818948813957974,
|
| 702 |
+
"learning_rate": 8.900742983451538e-06,
|
| 703 |
+
"loss": 2.2006,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.29711884753901563,
|
| 708 |
+
"grad_norm": 10.149928390127263,
|
| 709 |
+
"learning_rate": 8.867751527341962e-06,
|
| 710 |
+
"loss": 2.0095,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.30012004801920766,
|
| 715 |
+
"grad_norm": 8.46959243433518,
|
| 716 |
+
"learning_rate": 8.834335362607578e-06,
|
| 717 |
+
"loss": 1.8346,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.30012004801920766,
|
| 722 |
+
"eval_loss": 1.8436174392700195,
|
| 723 |
+
"eval_runtime": 70.088,
|
| 724 |
+
"eval_samples_per_second": 21.131,
|
| 725 |
+
"eval_steps_per_second": 10.572,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.30312124849939975,
|
| 730 |
+
"grad_norm": 16.868801651903272,
|
| 731 |
+
"learning_rate": 8.80049815859821e-06,
|
| 732 |
+
"loss": 1.9479,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.30612244897959184,
|
| 737 |
+
"grad_norm": 10.50023341524374,
|
| 738 |
+
"learning_rate": 8.766243630897002e-06,
|
| 739 |
+
"loss": 2.1128,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.30912364945978393,
|
| 744 |
+
"grad_norm": 8.928156526275373,
|
| 745 |
+
"learning_rate": 8.731575540912422e-06,
|
| 746 |
+
"loss": 1.9959,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.31212484993997597,
|
| 751 |
+
"grad_norm": 11.834343384295739,
|
| 752 |
+
"learning_rate": 8.696497695465237e-06,
|
| 753 |
+
"loss": 1.8446,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.31512605042016806,
|
| 758 |
+
"grad_norm": 14.438889863331674,
|
| 759 |
+
"learning_rate": 8.66101394637048e-06,
|
| 760 |
+
"loss": 1.9538,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.31812725090036015,
|
| 765 |
+
"grad_norm": 7.0509264901284405,
|
| 766 |
+
"learning_rate": 8.625128190014513e-06,
|
| 767 |
+
"loss": 2.224,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.32112845138055224,
|
| 772 |
+
"grad_norm": 10.882784743186303,
|
| 773 |
+
"learning_rate": 8.588844366927156e-06,
|
| 774 |
+
"loss": 1.9669,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.3241296518607443,
|
| 779 |
+
"grad_norm": 8.990237158612308,
|
| 780 |
+
"learning_rate": 8.552166461348991e-06,
|
| 781 |
+
"loss": 1.7175,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.32713085234093636,
|
| 786 |
+
"grad_norm": 14.10485370212862,
|
| 787 |
+
"learning_rate": 8.515098500793868e-06,
|
| 788 |
+
"loss": 1.9135,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.33013205282112845,
|
| 793 |
+
"grad_norm": 11.4270403766335,
|
| 794 |
+
"learning_rate": 8.477644555606647e-06,
|
| 795 |
+
"loss": 1.9181,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.33313325330132054,
|
| 800 |
+
"grad_norm": 10.98863933462178,
|
| 801 |
+
"learning_rate": 8.439808738516248e-06,
|
| 802 |
+
"loss": 2.0249,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.33613445378151263,
|
| 807 |
+
"grad_norm": 21.402837855150903,
|
| 808 |
+
"learning_rate": 8.401595204184035e-06,
|
| 809 |
+
"loss": 1.7287,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.33913565426170467,
|
| 814 |
+
"grad_norm": 13.977226200369794,
|
| 815 |
+
"learning_rate": 8.363008148747606e-06,
|
| 816 |
+
"loss": 1.7275,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.34213685474189676,
|
| 821 |
+
"grad_norm": 12.329315260812974,
|
| 822 |
+
"learning_rate": 8.324051809360037e-06,
|
| 823 |
+
"loss": 1.9854,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.34513805522208885,
|
| 828 |
+
"grad_norm": 6.8949526667461125,
|
| 829 |
+
"learning_rate": 8.284730463724585e-06,
|
| 830 |
+
"loss": 1.8173,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.34813925570228094,
|
| 835 |
+
"grad_norm": 15.132137249007318,
|
| 836 |
+
"learning_rate": 8.245048429624983e-06,
|
| 837 |
+
"loss": 2.0162,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.35114045618247297,
|
| 842 |
+
"grad_norm": 11.463625138426867,
|
| 843 |
+
"learning_rate": 8.205010064451314e-06,
|
| 844 |
+
"loss": 2.2115,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.35414165666266506,
|
| 849 |
+
"grad_norm": 12.725809570070531,
|
| 850 |
+
"learning_rate": 8.164619764721523e-06,
|
| 851 |
+
"loss": 2.204,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.35714285714285715,
|
| 856 |
+
"grad_norm": 12.730243560834372,
|
| 857 |
+
"learning_rate": 8.12388196559866e-06,
|
| 858 |
+
"loss": 1.897,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.36014405762304924,
|
| 863 |
+
"grad_norm": 7.029827177766862,
|
| 864 |
+
"learning_rate": 8.082801140403857e-06,
|
| 865 |
+
"loss": 1.7744,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.3631452581032413,
|
| 870 |
+
"grad_norm": 10.414460517503901,
|
| 871 |
+
"learning_rate": 8.041381800125129e-06,
|
| 872 |
+
"loss": 1.8452,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.36614645858343337,
|
| 877 |
+
"grad_norm": 13.745072092763401,
|
| 878 |
+
"learning_rate": 7.999628492922022e-06,
|
| 879 |
+
"loss": 2.0646,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.36914765906362546,
|
| 884 |
+
"grad_norm": 8.775551099349842,
|
| 885 |
+
"learning_rate": 7.957545803626208e-06,
|
| 886 |
+
"loss": 1.9013,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.37214885954381755,
|
| 891 |
+
"grad_norm": 12.599490709310933,
|
| 892 |
+
"learning_rate": 7.915138353238018e-06,
|
| 893 |
+
"loss": 2.0367,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.3751500600240096,
|
| 898 |
+
"grad_norm": 6.256535396667515,
|
| 899 |
+
"learning_rate": 7.872410798419033e-06,
|
| 900 |
+
"loss": 1.9974,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.37815126050420167,
|
| 905 |
+
"grad_norm": 9.33884703529061,
|
| 906 |
+
"learning_rate": 7.829367830980739e-06,
|
| 907 |
+
"loss": 1.9962,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.38115246098439376,
|
| 912 |
+
"grad_norm": 21.706114177368843,
|
| 913 |
+
"learning_rate": 7.786014177369336e-06,
|
| 914 |
+
"loss": 1.9969,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.38415366146458585,
|
| 919 |
+
"grad_norm": 12.19292284047377,
|
| 920 |
+
"learning_rate": 7.742354598146737e-06,
|
| 921 |
+
"loss": 2.0981,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3871548619447779,
|
| 926 |
+
"grad_norm": 9.306186302055167,
|
| 927 |
+
"learning_rate": 7.698393887467822e-06,
|
| 928 |
+
"loss": 1.9351,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.39015606242497,
|
| 933 |
+
"grad_norm": 7.075234259359012,
|
| 934 |
+
"learning_rate": 7.654136872553994e-06,
|
| 935 |
+
"loss": 2.0849,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.39315726290516206,
|
| 940 |
+
"grad_norm": 13.098710223009212,
|
| 941 |
+
"learning_rate": 7.609588413163133e-06,
|
| 942 |
+
"loss": 2.1268,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.39615846338535415,
|
| 947 |
+
"grad_norm": 8.116612120897077,
|
| 948 |
+
"learning_rate": 7.564753401055938e-06,
|
| 949 |
+
"loss": 2.1511,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.39915966386554624,
|
| 954 |
+
"grad_norm": 11.134740327279541,
|
| 955 |
+
"learning_rate": 7.519636759458787e-06,
|
| 956 |
+
"loss": 1.8251,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4021608643457383,
|
| 961 |
+
"grad_norm": 7.351044801101755,
|
| 962 |
+
"learning_rate": 7.474243442523122e-06,
|
| 963 |
+
"loss": 1.9105,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.40516206482593037,
|
| 968 |
+
"grad_norm": 13.084121400843905,
|
| 969 |
+
"learning_rate": 7.428578434781446e-06,
|
| 970 |
+
"loss": 2.0436,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.40816326530612246,
|
| 975 |
+
"grad_norm": 9.072398206431368,
|
| 976 |
+
"learning_rate": 7.382646750599991e-06,
|
| 977 |
+
"loss": 1.9403,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.41116446578631455,
|
| 982 |
+
"grad_norm": 10.586715140991426,
|
| 983 |
+
"learning_rate": 7.33645343362809e-06,
|
| 984 |
+
"loss": 2.0718,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.4141656662665066,
|
| 989 |
+
"grad_norm": 11.515109253824,
|
| 990 |
+
"learning_rate": 7.290003556244359e-06,
|
| 991 |
+
"loss": 1.8263,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4171668667466987,
|
| 996 |
+
"grad_norm": 11.730876807196703,
|
| 997 |
+
"learning_rate": 7.2433022189997e-06,
|
| 998 |
+
"loss": 1.9503,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.42016806722689076,
|
| 1003 |
+
"grad_norm": 10.550292645454324,
|
| 1004 |
+
"learning_rate": 7.196354550057226e-06,
|
| 1005 |
+
"loss": 1.8239,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.42316926770708285,
|
| 1010 |
+
"grad_norm": 9.887874814498124,
|
| 1011 |
+
"learning_rate": 7.1491657046291526e-06,
|
| 1012 |
+
"loss": 1.9299,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4261704681872749,
|
| 1017 |
+
"grad_norm": 12.616008529269662,
|
| 1018 |
+
"learning_rate": 7.101740864410709e-06,
|
| 1019 |
+
"loss": 2.1525,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.429171668667467,
|
| 1024 |
+
"grad_norm": 8.812376323246953,
|
| 1025 |
+
"learning_rate": 7.05408523701116e-06,
|
| 1026 |
+
"loss": 1.8238,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.43217286914765907,
|
| 1031 |
+
"grad_norm": 8.745128290955817,
|
| 1032 |
+
"learning_rate": 7.006204055381957e-06,
|
| 1033 |
+
"loss": 1.6758,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.43517406962785116,
|
| 1038 |
+
"grad_norm": 6.318402234130335,
|
| 1039 |
+
"learning_rate": 6.958102577242128e-06,
|
| 1040 |
+
"loss": 1.9202,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.4381752701080432,
|
| 1045 |
+
"grad_norm": 7.927574856182854,
|
| 1046 |
+
"learning_rate": 6.909786084500939e-06,
|
| 1047 |
+
"loss": 2.0833,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4411764705882353,
|
| 1052 |
+
"grad_norm": 10.544936971680398,
|
| 1053 |
+
"learning_rate": 6.861259882677902e-06,
|
| 1054 |
+
"loss": 2.002,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.44417767106842737,
|
| 1059 |
+
"grad_norm": 11.619710218418861,
|
| 1060 |
+
"learning_rate": 6.8125293003201806e-06,
|
| 1061 |
+
"loss": 1.7993,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.44717887154861946,
|
| 1066 |
+
"grad_norm": 6.420503958767878,
|
| 1067 |
+
"learning_rate": 6.763599688417487e-06,
|
| 1068 |
+
"loss": 1.8841,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.45018007202881155,
|
| 1073 |
+
"grad_norm": 12.533300979520721,
|
| 1074 |
+
"learning_rate": 6.714476419814492e-06,
|
| 1075 |
+
"loss": 1.9325,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.45018007202881155,
|
| 1080 |
+
"eval_loss": 1.7854255437850952,
|
| 1081 |
+
"eval_runtime": 72.7355,
|
| 1082 |
+
"eval_samples_per_second": 20.361,
|
| 1083 |
+
"eval_steps_per_second": 10.188,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.4531812725090036,
|
| 1088 |
+
"grad_norm": 4.747847172239305,
|
| 1089 |
+
"learning_rate": 6.665164888620848e-06,
|
| 1090 |
+
"loss": 1.6663,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.4561824729891957,
|
| 1095 |
+
"grad_norm": 7.525229479358654,
|
| 1096 |
+
"learning_rate": 6.615670509618879e-06,
|
| 1097 |
+
"loss": 1.6184,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.45918367346938777,
|
| 1102 |
+
"grad_norm": 9.73553436099885,
|
| 1103 |
+
"learning_rate": 6.565998717668992e-06,
|
| 1104 |
+
"loss": 2.0157,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.46218487394957986,
|
| 1109 |
+
"grad_norm": 1.9365788113666345,
|
| 1110 |
+
"learning_rate": 6.516154967112891e-06,
|
| 1111 |
+
"loss": 1.5343,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.4651860744297719,
|
| 1116 |
+
"grad_norm": 13.65674435295188,
|
| 1117 |
+
"learning_rate": 6.466144731174645e-06,
|
| 1118 |
+
"loss": 1.8785,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.468187274909964,
|
| 1123 |
+
"grad_norm": 12.365721091880623,
|
| 1124 |
+
"learning_rate": 6.415973501359687e-06,
|
| 1125 |
+
"loss": 1.7204,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.47118847539015607,
|
| 1130 |
+
"grad_norm": 6.498996459559609,
|
| 1131 |
+
"learning_rate": 6.365646786851809e-06,
|
| 1132 |
+
"loss": 1.9123,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.47418967587034816,
|
| 1137 |
+
"grad_norm": 12.248966426285023,
|
| 1138 |
+
"learning_rate": 6.315170113908204e-06,
|
| 1139 |
+
"loss": 2.0724,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.4771908763505402,
|
| 1144 |
+
"grad_norm": 6.254751069477799,
|
| 1145 |
+
"learning_rate": 6.264549025252652e-06,
|
| 1146 |
+
"loss": 2.0417,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4801920768307323,
|
| 1151 |
+
"grad_norm": 11.586505827936087,
|
| 1152 |
+
"learning_rate": 6.213789079466873e-06,
|
| 1153 |
+
"loss": 1.9998,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4831932773109244,
|
| 1158 |
+
"grad_norm": 11.628169667737911,
|
| 1159 |
+
"learning_rate": 6.1628958503801635e-06,
|
| 1160 |
+
"loss": 1.9805,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.48619447779111646,
|
| 1165 |
+
"grad_norm": 10.266695075168396,
|
| 1166 |
+
"learning_rate": 6.111874926457344e-06,
|
| 1167 |
+
"loss": 1.9866,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.4891956782713085,
|
| 1172 |
+
"grad_norm": 7.864602445607685,
|
| 1173 |
+
"learning_rate": 6.0607319101850955e-06,
|
| 1174 |
+
"loss": 2.0325,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4921968787515006,
|
| 1179 |
+
"grad_norm": 7.852131699169073,
|
| 1180 |
+
"learning_rate": 6.009472417456779e-06,
|
| 1181 |
+
"loss": 2.136,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4951980792316927,
|
| 1186 |
+
"grad_norm": 9.171127473935298,
|
| 1187 |
+
"learning_rate": 5.958102076955753e-06,
|
| 1188 |
+
"loss": 1.8371,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.49819927971188477,
|
| 1193 |
+
"grad_norm": 13.155484650564988,
|
| 1194 |
+
"learning_rate": 5.906626529537311e-06,
|
| 1195 |
+
"loss": 2.1112,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.5012004801920769,
|
| 1200 |
+
"grad_norm": 14.407405269785295,
|
| 1201 |
+
"learning_rate": 5.855051427609265e-06,
|
| 1202 |
+
"loss": 2.1317,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.5042016806722689,
|
| 1207 |
+
"grad_norm": 7.944398594556855,
|
| 1208 |
+
"learning_rate": 5.803382434511274e-06,
|
| 1209 |
+
"loss": 1.9131,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.507202881152461,
|
| 1214 |
+
"grad_norm": 12.067931060345453,
|
| 1215 |
+
"learning_rate": 5.751625223892964e-06,
|
| 1216 |
+
"loss": 1.961,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.5102040816326531,
|
| 1221 |
+
"grad_norm": 11.305421590297874,
|
| 1222 |
+
"learning_rate": 5.699785479090917e-06,
|
| 1223 |
+
"loss": 1.8233,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.5132052821128451,
|
| 1228 |
+
"grad_norm": 10.568805120830348,
|
| 1229 |
+
"learning_rate": 5.647868892504597e-06,
|
| 1230 |
+
"loss": 1.8034,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.5162064825930373,
|
| 1235 |
+
"grad_norm": 8.901920906884708,
|
| 1236 |
+
"learning_rate": 5.595881164971284e-06,
|
| 1237 |
+
"loss": 2.1088,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.5192076830732293,
|
| 1242 |
+
"grad_norm": 10.818151872015115,
|
| 1243 |
+
"learning_rate": 5.543828005140076e-06,
|
| 1244 |
+
"loss": 1.9505,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.5222088835534213,
|
| 1249 |
+
"grad_norm": 19.0269528128246,
|
| 1250 |
+
"learning_rate": 5.491715128845037e-06,
|
| 1251 |
+
"loss": 2.1158,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.5252100840336135,
|
| 1256 |
+
"grad_norm": 6.368156672789348,
|
| 1257 |
+
"learning_rate": 5.439548258477549e-06,
|
| 1258 |
+
"loss": 1.526,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.5282112845138055,
|
| 1263 |
+
"grad_norm": 14.33226946197169,
|
| 1264 |
+
"learning_rate": 5.387333122357966e-06,
|
| 1265 |
+
"loss": 1.9441,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5312124849939976,
|
| 1270 |
+
"grad_norm": 10.893640588904004,
|
| 1271 |
+
"learning_rate": 5.3350754541065805e-06,
|
| 1272 |
+
"loss": 1.5771,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5342136854741897,
|
| 1277 |
+
"grad_norm": 11.613038829759443,
|
| 1278 |
+
"learning_rate": 5.282780992014043e-06,
|
| 1279 |
+
"loss": 1.8335,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.5372148859543817,
|
| 1284 |
+
"grad_norm": 6.446614047723568,
|
| 1285 |
+
"learning_rate": 5.230455478411243e-06,
|
| 1286 |
+
"loss": 1.9638,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5402160864345739,
|
| 1291 |
+
"grad_norm": 14.258595482993,
|
| 1292 |
+
"learning_rate": 5.1781046590387675e-06,
|
| 1293 |
+
"loss": 1.8887,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.5432172869147659,
|
| 1298 |
+
"grad_norm": 10.102795668494593,
|
| 1299 |
+
"learning_rate": 5.125734282415967e-06,
|
| 1300 |
+
"loss": 2.1767,
|
| 1301 |
+
"step": 1810
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5462184873949579,
|
| 1305 |
+
"grad_norm": 11.29991368417218,
|
| 1306 |
+
"learning_rate": 5.0733500992097295e-06,
|
| 1307 |
+
"loss": 1.8136,
|
| 1308 |
+
"step": 1820
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.5492196878751501,
|
| 1312 |
+
"grad_norm": 5.146344981754679,
|
| 1313 |
+
"learning_rate": 5.020957861603011e-06,
|
| 1314 |
+
"loss": 1.6411,
|
| 1315 |
+
"step": 1830
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5522208883553421,
|
| 1319 |
+
"grad_norm": 14.066643454727922,
|
| 1320 |
+
"learning_rate": 4.9685633226632004e-06,
|
| 1321 |
+
"loss": 1.8657,
|
| 1322 |
+
"step": 1840
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5552220888355343,
|
| 1326 |
+
"grad_norm": 9.885151028744932,
|
| 1327 |
+
"learning_rate": 4.916172235710393e-06,
|
| 1328 |
+
"loss": 1.8143,
|
| 1329 |
+
"step": 1850
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5582232893157263,
|
| 1333 |
+
"grad_norm": 11.550762892952077,
|
| 1334 |
+
"learning_rate": 4.8637903536856266e-06,
|
| 1335 |
+
"loss": 1.9513,
|
| 1336 |
+
"step": 1860
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5612244897959183,
|
| 1340 |
+
"grad_norm": 16.261531223174785,
|
| 1341 |
+
"learning_rate": 4.811423428519169e-06,
|
| 1342 |
+
"loss": 1.6205,
|
| 1343 |
+
"step": 1870
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5642256902761105,
|
| 1347 |
+
"grad_norm": 11.38322225643573,
|
| 1348 |
+
"learning_rate": 4.759077210498913e-06,
|
| 1349 |
+
"loss": 1.7196,
|
| 1350 |
+
"step": 1880
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5672268907563025,
|
| 1354 |
+
"grad_norm": 8.776094085092314,
|
| 1355 |
+
"learning_rate": 4.706757447638945e-06,
|
| 1356 |
+
"loss": 2.0409,
|
| 1357 |
+
"step": 1890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5702280912364946,
|
| 1361 |
+
"grad_norm": 9.049484315692625,
|
| 1362 |
+
"learning_rate": 4.654469885048376e-06,
|
| 1363 |
+
"loss": 1.9866,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.5732292917166867,
|
| 1368 |
+
"grad_norm": 10.657785810994662,
|
| 1369 |
+
"learning_rate": 4.602220264300481e-06,
|
| 1370 |
+
"loss": 1.8922,
|
| 1371 |
+
"step": 1910
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5762304921968787,
|
| 1375 |
+
"grad_norm": 9.342865110666766,
|
| 1376 |
+
"learning_rate": 4.55001432280223e-06,
|
| 1377 |
+
"loss": 1.7542,
|
| 1378 |
+
"step": 1920
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5792316926770709,
|
| 1382 |
+
"grad_norm": 12.081799903070168,
|
| 1383 |
+
"learning_rate": 4.497857793164277e-06,
|
| 1384 |
+
"loss": 1.9913,
|
| 1385 |
+
"step": 1930
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5822328931572629,
|
| 1389 |
+
"grad_norm": 7.619917781656242,
|
| 1390 |
+
"learning_rate": 4.445756402571483e-06,
|
| 1391 |
+
"loss": 1.9881,
|
| 1392 |
+
"step": 1940
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5852340936374549,
|
| 1396 |
+
"grad_norm": 9.093969376778242,
|
| 1397 |
+
"learning_rate": 4.393715872154014e-06,
|
| 1398 |
+
"loss": 1.7711,
|
| 1399 |
+
"step": 1950
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5882352941176471,
|
| 1403 |
+
"grad_norm": 9.108154177538303,
|
| 1404 |
+
"learning_rate": 4.3417419163591296e-06,
|
| 1405 |
+
"loss": 1.7914,
|
| 1406 |
+
"step": 1960
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5912364945978391,
|
| 1410 |
+
"grad_norm": 9.864863366342805,
|
| 1411 |
+
"learning_rate": 4.2898402423236835e-06,
|
| 1412 |
+
"loss": 1.7734,
|
| 1413 |
+
"step": 1970
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5942376950780313,
|
| 1417 |
+
"grad_norm": 14.65031277951791,
|
| 1418 |
+
"learning_rate": 4.238016549247443e-06,
|
| 1419 |
+
"loss": 1.8682,
|
| 1420 |
+
"step": 1980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.5972388955582233,
|
| 1424 |
+
"grad_norm": 15.195046706414468,
|
| 1425 |
+
"learning_rate": 4.186276527767273e-06,
|
| 1426 |
+
"loss": 1.8358,
|
| 1427 |
+
"step": 1990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.6002400960384153,
|
| 1431 |
+
"grad_norm": 7.420521707718542,
|
| 1432 |
+
"learning_rate": 4.1346258593322555e-06,
|
| 1433 |
+
"loss": 1.8923,
|
| 1434 |
+
"step": 2000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.6002400960384153,
|
| 1438 |
+
"eval_loss": 1.7435638904571533,
|
| 1439 |
+
"eval_runtime": 69.2816,
|
| 1440 |
+
"eval_samples_per_second": 21.377,
|
| 1441 |
+
"eval_steps_per_second": 10.695,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.6032412965186075,
|
| 1446 |
+
"grad_norm": 25.45598758249549,
|
| 1447 |
+
"learning_rate": 4.08307021557983e-06,
|
| 1448 |
+
"loss": 1.7191,
|
| 1449 |
+
"step": 2010
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.6062424969987995,
|
| 1453 |
+
"grad_norm": 7.897349852896533,
|
| 1454 |
+
"learning_rate": 4.031615257712996e-06,
|
| 1455 |
+
"loss": 1.9881,
|
| 1456 |
+
"step": 2020
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.6092436974789915,
|
| 1460 |
+
"grad_norm": 6.16625120190022,
|
| 1461 |
+
"learning_rate": 3.98026663587868e-06,
|
| 1462 |
+
"loss": 1.7836,
|
| 1463 |
+
"step": 2030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.6122448979591837,
|
| 1467 |
+
"grad_norm": 20.615497493186695,
|
| 1468 |
+
"learning_rate": 3.929029988547296e-06,
|
| 1469 |
+
"loss": 1.9693,
|
| 1470 |
+
"step": 2040
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.6152460984393757,
|
| 1474 |
+
"grad_norm": 16.331083465757896,
|
| 1475 |
+
"learning_rate": 3.8779109418936074e-06,
|
| 1476 |
+
"loss": 1.9877,
|
| 1477 |
+
"step": 2050
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.6182472989195679,
|
| 1481 |
+
"grad_norm": 8.975255093028004,
|
| 1482 |
+
"learning_rate": 3.826915109178925e-06,
|
| 1483 |
+
"loss": 1.7951,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.6212484993997599,
|
| 1488 |
+
"grad_norm": 14.614156710342609,
|
| 1489 |
+
"learning_rate": 3.776048090134726e-06,
|
| 1490 |
+
"loss": 2.0532,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.6242496998799519,
|
| 1495 |
+
"grad_norm": 14.227607937991625,
|
| 1496 |
+
"learning_rate": 3.725315470347769e-06,
|
| 1497 |
+
"loss": 1.6202,
|
| 1498 |
+
"step": 2080
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.6272509003601441,
|
| 1502 |
+
"grad_norm": 9.755464711787543,
|
| 1503 |
+
"learning_rate": 3.6747228206467435e-06,
|
| 1504 |
+
"loss": 1.8552,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.6302521008403361,
|
| 1509 |
+
"grad_norm": 11.720295448594253,
|
| 1510 |
+
"learning_rate": 3.62427569649056e-06,
|
| 1511 |
+
"loss": 2.0746,
|
| 1512 |
+
"step": 2100
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.6332533013205283,
|
| 1516 |
+
"grad_norm": 12.420750898009793,
|
| 1517 |
+
"learning_rate": 3.5739796373583124e-06,
|
| 1518 |
+
"loss": 1.9033,
|
| 1519 |
+
"step": 2110
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.6362545018007203,
|
| 1523 |
+
"grad_norm": 18.15546870310451,
|
| 1524 |
+
"learning_rate": 3.5238401661410016e-06,
|
| 1525 |
+
"loss": 1.949,
|
| 1526 |
+
"step": 2120
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.6392557022809123,
|
| 1530 |
+
"grad_norm": 8.838596253346461,
|
| 1531 |
+
"learning_rate": 3.473862788535083e-06,
|
| 1532 |
+
"loss": 1.9731,
|
| 1533 |
+
"step": 2130
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.6422569027611045,
|
| 1537 |
+
"grad_norm": 7.021128179443776,
|
| 1538 |
+
"learning_rate": 3.4240529924378933e-06,
|
| 1539 |
+
"loss": 1.6426,
|
| 1540 |
+
"step": 2140
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.6452581032412965,
|
| 1544 |
+
"grad_norm": 16.281499993295807,
|
| 1545 |
+
"learning_rate": 3.3744162473450435e-06,
|
| 1546 |
+
"loss": 1.7679,
|
| 1547 |
+
"step": 2150
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.6482593037214885,
|
| 1551 |
+
"grad_norm": 8.482637058307281,
|
| 1552 |
+
"learning_rate": 3.3249580037498263e-06,
|
| 1553 |
+
"loss": 1.9333,
|
| 1554 |
+
"step": 2160
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.6512605042016807,
|
| 1558 |
+
"grad_norm": 5.789850691609375,
|
| 1559 |
+
"learning_rate": 3.2756836925447044e-06,
|
| 1560 |
+
"loss": 1.9397,
|
| 1561 |
+
"step": 2170
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.6542617046818727,
|
| 1565 |
+
"grad_norm": 11.068102019401588,
|
| 1566 |
+
"learning_rate": 3.226598724424961e-06,
|
| 1567 |
+
"loss": 1.7214,
|
| 1568 |
+
"step": 2180
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.6572629051620649,
|
| 1572 |
+
"grad_norm": 9.416049920187813,
|
| 1573 |
+
"learning_rate": 3.177708489294567e-06,
|
| 1574 |
+
"loss": 1.9513,
|
| 1575 |
+
"step": 2190
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.6602641056422569,
|
| 1579 |
+
"grad_norm": 10.76548308072494,
|
| 1580 |
+
"learning_rate": 3.1290183556743215e-06,
|
| 1581 |
+
"loss": 1.8658,
|
| 1582 |
+
"step": 2200
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.6632653061224489,
|
| 1586 |
+
"grad_norm": 8.315082778946813,
|
| 1587 |
+
"learning_rate": 3.0805336701123555e-06,
|
| 1588 |
+
"loss": 1.9731,
|
| 1589 |
+
"step": 2210
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.6662665066026411,
|
| 1593 |
+
"grad_norm": 11.29084985203435,
|
| 1594 |
+
"learning_rate": 3.0322597565970336e-06,
|
| 1595 |
+
"loss": 1.8275,
|
| 1596 |
+
"step": 2220
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.6692677070828331,
|
| 1600 |
+
"grad_norm": 10.819151083740058,
|
| 1601 |
+
"learning_rate": 2.98420191597234e-06,
|
| 1602 |
+
"loss": 1.8203,
|
| 1603 |
+
"step": 2230
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.6722689075630253,
|
| 1607 |
+
"grad_norm": 5.702362844533201,
|
| 1608 |
+
"learning_rate": 2.9363654253558112e-06,
|
| 1609 |
+
"loss": 1.6585,
|
| 1610 |
+
"step": 2240
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.6752701080432173,
|
| 1614 |
+
"grad_norm": 5.380869015585197,
|
| 1615 |
+
"learning_rate": 2.888755537559059e-06,
|
| 1616 |
+
"loss": 1.8569,
|
| 1617 |
+
"step": 2250
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.6782713085234093,
|
| 1621 |
+
"grad_norm": 8.643150027971613,
|
| 1622 |
+
"learning_rate": 2.8413774805109816e-06,
|
| 1623 |
+
"loss": 1.6714,
|
| 1624 |
+
"step": 2260
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.6812725090036015,
|
| 1628 |
+
"grad_norm": 11.634468465567483,
|
| 1629 |
+
"learning_rate": 2.794236456683691e-06,
|
| 1630 |
+
"loss": 1.7458,
|
| 1631 |
+
"step": 2270
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.6842737094837935,
|
| 1635 |
+
"grad_norm": 5.301188602330632,
|
| 1636 |
+
"learning_rate": 2.7473376425212415e-06,
|
| 1637 |
+
"loss": 2.04,
|
| 1638 |
+
"step": 2280
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.6872749099639855,
|
| 1642 |
+
"grad_norm": 9.693536388062485,
|
| 1643 |
+
"learning_rate": 2.7006861878712193e-06,
|
| 1644 |
+
"loss": 1.9511,
|
| 1645 |
+
"step": 2290
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.6902761104441777,
|
| 1649 |
+
"grad_norm": 10.486571882103618,
|
| 1650 |
+
"learning_rate": 2.65428721541925e-06,
|
| 1651 |
+
"loss": 1.738,
|
| 1652 |
+
"step": 2300
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.6932773109243697,
|
| 1656 |
+
"grad_norm": 9.714557073333323,
|
| 1657 |
+
"learning_rate": 2.608145820126486e-06,
|
| 1658 |
+
"loss": 1.9507,
|
| 1659 |
+
"step": 2310
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.6962785114045619,
|
| 1663 |
+
"grad_norm": 9.429193711409267,
|
| 1664 |
+
"learning_rate": 2.5622670686701445e-06,
|
| 1665 |
+
"loss": 1.8208,
|
| 1666 |
+
"step": 2320
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.6992797118847539,
|
| 1670 |
+
"grad_norm": 9.732041067448783,
|
| 1671 |
+
"learning_rate": 2.5166559988871436e-06,
|
| 1672 |
+
"loss": 1.6763,
|
| 1673 |
+
"step": 2330
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.7022809123649459,
|
| 1677 |
+
"grad_norm": 7.057685729051554,
|
| 1678 |
+
"learning_rate": 2.4713176192209117e-06,
|
| 1679 |
+
"loss": 1.9426,
|
| 1680 |
+
"step": 2340
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.7052821128451381,
|
| 1684 |
+
"grad_norm": 8.918715713654343,
|
| 1685 |
+
"learning_rate": 2.4262569081714267e-06,
|
| 1686 |
+
"loss": 1.6474,
|
| 1687 |
+
"step": 2350
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.7082833133253301,
|
| 1691 |
+
"grad_norm": 9.709979676554493,
|
| 1692 |
+
"learning_rate": 2.3814788137485274e-06,
|
| 1693 |
+
"loss": 1.755,
|
| 1694 |
+
"step": 2360
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.7112845138055222,
|
| 1698 |
+
"grad_norm": 10.928425359376956,
|
| 1699 |
+
"learning_rate": 2.3369882529285946e-06,
|
| 1700 |
+
"loss": 1.8029,
|
| 1701 |
+
"step": 2370
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.7142857142857143,
|
| 1705 |
+
"grad_norm": 7.175795498617987,
|
| 1706 |
+
"learning_rate": 2.2927901111146257e-06,
|
| 1707 |
+
"loss": 1.7256,
|
| 1708 |
+
"step": 2380
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.7172869147659063,
|
| 1712 |
+
"grad_norm": 18.14134056680293,
|
| 1713 |
+
"learning_rate": 2.2488892415997785e-06,
|
| 1714 |
+
"loss": 2.0907,
|
| 1715 |
+
"step": 2390
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.7202881152460985,
|
| 1719 |
+
"grad_norm": 6.717240701355819,
|
| 1720 |
+
"learning_rate": 2.205290465034447e-06,
|
| 1721 |
+
"loss": 1.5589,
|
| 1722 |
+
"step": 2400
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.7232893157262905,
|
| 1726 |
+
"grad_norm": 12.168333129288724,
|
| 1727 |
+
"learning_rate": 2.161998568896912e-06,
|
| 1728 |
+
"loss": 1.8209,
|
| 1729 |
+
"step": 2410
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.7262905162064826,
|
| 1733 |
+
"grad_norm": 10.741569883466353,
|
| 1734 |
+
"learning_rate": 2.119018306967645e-06,
|
| 1735 |
+
"loss": 1.971,
|
| 1736 |
+
"step": 2420
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.7292917166866747,
|
| 1740 |
+
"grad_norm": 16.111952110701104,
|
| 1741 |
+
"learning_rate": 2.076354398807302e-06,
|
| 1742 |
+
"loss": 2.0432,
|
| 1743 |
+
"step": 2430
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.7322929171668667,
|
| 1747 |
+
"grad_norm": 13.142283229532243,
|
| 1748 |
+
"learning_rate": 2.0340115292384823e-06,
|
| 1749 |
+
"loss": 1.9268,
|
| 1750 |
+
"step": 2440
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.7352941176470589,
|
| 1754 |
+
"grad_norm": 13.878662825779742,
|
| 1755 |
+
"learning_rate": 1.991994347831296e-06,
|
| 1756 |
+
"loss": 1.7237,
|
| 1757 |
+
"step": 2450
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.7382953181272509,
|
| 1761 |
+
"grad_norm": 5.193419227304116,
|
| 1762 |
+
"learning_rate": 1.950307468392816e-06,
|
| 1763 |
+
"loss": 1.5961,
|
| 1764 |
+
"step": 2460
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.741296518607443,
|
| 1768 |
+
"grad_norm": 9.681305775895257,
|
| 1769 |
+
"learning_rate": 1.908955468460431e-06,
|
| 1770 |
+
"loss": 1.7885,
|
| 1771 |
+
"step": 2470
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.7442977190876351,
|
| 1775 |
+
"grad_norm": 7.345155776831447,
|
| 1776 |
+
"learning_rate": 1.8679428887992091e-06,
|
| 1777 |
+
"loss": 1.7101,
|
| 1778 |
+
"step": 2480
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.7472989195678271,
|
| 1782 |
+
"grad_norm": 9.404415925054249,
|
| 1783 |
+
"learning_rate": 1.8272742329032823e-06,
|
| 1784 |
+
"loss": 1.6541,
|
| 1785 |
+
"step": 2490
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.7503001200480192,
|
| 1789 |
+
"grad_norm": 8.942445965443895,
|
| 1790 |
+
"learning_rate": 1.786953966501329e-06,
|
| 1791 |
+
"loss": 1.8412,
|
| 1792 |
+
"step": 2500
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.7503001200480192,
|
| 1796 |
+
"eval_loss": 1.7098486423492432,
|
| 1797 |
+
"eval_runtime": 69.0609,
|
| 1798 |
+
"eval_samples_per_second": 21.445,
|
| 1799 |
+
"eval_steps_per_second": 10.73,
|
| 1800 |
+
"step": 2500
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.7533013205282113,
|
| 1804 |
+
"grad_norm": 7.112796773683413,
|
| 1805 |
+
"learning_rate": 1.7469865170662042e-06,
|
| 1806 |
+
"loss": 1.7868,
|
| 1807 |
+
"step": 2510
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.7563025210084033,
|
| 1811 |
+
"grad_norm": 10.215324534084571,
|
| 1812 |
+
"learning_rate": 1.7073762733287673e-06,
|
| 1813 |
+
"loss": 1.9726,
|
| 1814 |
+
"step": 2520
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.7593037214885955,
|
| 1818 |
+
"grad_norm": 8.971281702817224,
|
| 1819 |
+
"learning_rate": 1.6681275847959682e-06,
|
| 1820 |
+
"loss": 1.9379,
|
| 1821 |
+
"step": 2530
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.7623049219687875,
|
| 1825 |
+
"grad_norm": 5.252619106379976,
|
| 1826 |
+
"learning_rate": 1.629244761273236e-06,
|
| 1827 |
+
"loss": 1.9052,
|
| 1828 |
+
"step": 2540
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.7653061224489796,
|
| 1832 |
+
"grad_norm": 12.979254662689454,
|
| 1833 |
+
"learning_rate": 1.59073207239123e-06,
|
| 1834 |
+
"loss": 1.7957,
|
| 1835 |
+
"step": 2550
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.7683073229291717,
|
| 1839 |
+
"grad_norm": 14.54402968789474,
|
| 1840 |
+
"learning_rate": 1.5525937471370028e-06,
|
| 1841 |
+
"loss": 1.8423,
|
| 1842 |
+
"step": 2560
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.7713085234093637,
|
| 1846 |
+
"grad_norm": 9.927862797074557,
|
| 1847 |
+
"learning_rate": 1.5148339733896273e-06,
|
| 1848 |
+
"loss": 1.8718,
|
| 1849 |
+
"step": 2570
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.7743097238895558,
|
| 1853 |
+
"grad_norm": 7.939709500391649,
|
| 1854 |
+
"learning_rate": 1.4774568974603288e-06,
|
| 1855 |
+
"loss": 1.7308,
|
| 1856 |
+
"step": 2580
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.7773109243697479,
|
| 1860 |
+
"grad_norm": 12.312074651195383,
|
| 1861 |
+
"learning_rate": 1.4404666236371945e-06,
|
| 1862 |
+
"loss": 1.9014,
|
| 1863 |
+
"step": 2590
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.78031212484994,
|
| 1867 |
+
"grad_norm": 10.220811481679306,
|
| 1868 |
+
"learning_rate": 1.403867213734489e-06,
|
| 1869 |
+
"loss": 1.7677,
|
| 1870 |
+
"step": 2600
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.7833133253301321,
|
| 1874 |
+
"grad_norm": 19.399508227144526,
|
| 1875 |
+
"learning_rate": 1.3676626866466375e-06,
|
| 1876 |
+
"loss": 1.788,
|
| 1877 |
+
"step": 2610
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.7863145258103241,
|
| 1881 |
+
"grad_norm": 9.2503917337496,
|
| 1882 |
+
"learning_rate": 1.3318570179069185e-06,
|
| 1883 |
+
"loss": 2.0625,
|
| 1884 |
+
"step": 2620
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.7893157262905162,
|
| 1888 |
+
"grad_norm": 8.911090468997303,
|
| 1889 |
+
"learning_rate": 1.2964541392509206e-06,
|
| 1890 |
+
"loss": 1.9352,
|
| 1891 |
+
"step": 2630
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.7923169267707083,
|
| 1895 |
+
"grad_norm": 12.598406658927978,
|
| 1896 |
+
"learning_rate": 1.2614579381848097e-06,
|
| 1897 |
+
"loss": 1.723,
|
| 1898 |
+
"step": 2640
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.7953181272509003,
|
| 1902 |
+
"grad_norm": 21.484696683902342,
|
| 1903 |
+
"learning_rate": 1.2268722575584491e-06,
|
| 1904 |
+
"loss": 2.131,
|
| 1905 |
+
"step": 2650
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.7983193277310925,
|
| 1909 |
+
"grad_norm": 13.298645692955851,
|
| 1910 |
+
"learning_rate": 1.192700895143426e-06,
|
| 1911 |
+
"loss": 1.7506,
|
| 1912 |
+
"step": 2660
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.8013205282112845,
|
| 1916 |
+
"grad_norm": 10.538703379522518,
|
| 1917 |
+
"learning_rate": 1.1589476032160258e-06,
|
| 1918 |
+
"loss": 1.7293,
|
| 1919 |
+
"step": 2670
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.8043217286914766,
|
| 1923 |
+
"grad_norm": 12.739887717832003,
|
| 1924 |
+
"learning_rate": 1.1256160881452083e-06,
|
| 1925 |
+
"loss": 1.7933,
|
| 1926 |
+
"step": 2680
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.8073229291716687,
|
| 1930 |
+
"grad_norm": 14.360620984630774,
|
| 1931 |
+
"learning_rate": 1.0927100099856142e-06,
|
| 1932 |
+
"loss": 1.8849,
|
| 1933 |
+
"step": 2690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.8103241296518607,
|
| 1937 |
+
"grad_norm": 5.989428393509824,
|
| 1938 |
+
"learning_rate": 1.0602329820756657e-06,
|
| 1939 |
+
"loss": 1.7125,
|
| 1940 |
+
"step": 2700
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.8133253301320528,
|
| 1944 |
+
"grad_norm": 10.651430053252357,
|
| 1945 |
+
"learning_rate": 1.0281885706407946e-06,
|
| 1946 |
+
"loss": 1.6753,
|
| 1947 |
+
"step": 2710
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.8163265306122449,
|
| 1951 |
+
"grad_norm": 12.721788569785847,
|
| 1952 |
+
"learning_rate": 9.965802944018439e-07,
|
| 1953 |
+
"loss": 1.7935,
|
| 1954 |
+
"step": 2720
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.819327731092437,
|
| 1958 |
+
"grad_norm": 6.935894808100623,
|
| 1959 |
+
"learning_rate": 9.654116241886835e-07,
|
| 1960 |
+
"loss": 1.7312,
|
| 1961 |
+
"step": 2730
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.8223289315726291,
|
| 1965 |
+
"grad_norm": 14.90437859224957,
|
| 1966 |
+
"learning_rate": 9.346859825590898e-07,
|
| 1967 |
+
"loss": 1.9238,
|
| 1968 |
+
"step": 2740
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.8253301320528211,
|
| 1972 |
+
"grad_norm": 12.847343417287242,
|
| 1973 |
+
"learning_rate": 9.044067434229198e-07,
|
| 1974 |
+
"loss": 1.8688,
|
| 1975 |
+
"step": 2750
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.8283313325330132,
|
| 1979 |
+
"grad_norm": 7.720677688104362,
|
| 1980 |
+
"learning_rate": 8.745772316716306e-07,
|
| 1981 |
+
"loss": 1.5514,
|
| 1982 |
+
"step": 2760
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.8313325330132053,
|
| 1986 |
+
"grad_norm": 10.636415880249098,
|
| 1987 |
+
"learning_rate": 8.45200722813182e-07,
|
| 1988 |
+
"loss": 2.0041,
|
| 1989 |
+
"step": 2770
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.8343337334933973,
|
| 1993 |
+
"grad_norm": 7.134978636658263,
|
| 1994 |
+
"learning_rate": 8.162804426123599e-07,
|
| 1995 |
+
"loss": 1.8857,
|
| 1996 |
+
"step": 2780
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.8373349339735895,
|
| 2000 |
+
"grad_norm": 8.362149031227958,
|
| 2001 |
+
"learning_rate": 7.878195667365645e-07,
|
| 2002 |
+
"loss": 1.6578,
|
| 2003 |
+
"step": 2790
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.8403361344537815,
|
| 2007 |
+
"grad_norm": 10.181725570499646,
|
| 2008 |
+
"learning_rate": 7.598212204070954e-07,
|
| 2009 |
+
"loss": 1.7818,
|
| 2010 |
+
"step": 2800
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.8433373349339736,
|
| 2014 |
+
"grad_norm": 8.20212362723166,
|
| 2015 |
+
"learning_rate": 7.322884780559781e-07,
|
| 2016 |
+
"loss": 1.768,
|
| 2017 |
+
"step": 2810
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.8463385354141657,
|
| 2021 |
+
"grad_norm": 12.11494077921602,
|
| 2022 |
+
"learning_rate": 7.05224362988371e-07,
|
| 2023 |
+
"loss": 1.8017,
|
| 2024 |
+
"step": 2820
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.8493397358943577,
|
| 2028 |
+
"grad_norm": 7.615432940710001,
|
| 2029 |
+
"learning_rate": 6.786318470505798e-07,
|
| 2030 |
+
"loss": 1.847,
|
| 2031 |
+
"step": 2830
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.8523409363745498,
|
| 2035 |
+
"grad_norm": 13.508321765586018,
|
| 2036 |
+
"learning_rate": 6.525138503037299e-07,
|
| 2037 |
+
"loss": 1.8985,
|
| 2038 |
+
"step": 2840
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.8553421368547419,
|
| 2042 |
+
"grad_norm": 16.276142623089523,
|
| 2043 |
+
"learning_rate": 6.26873240703118e-07,
|
| 2044 |
+
"loss": 2.0172,
|
| 2045 |
+
"step": 2850
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.858343337334934,
|
| 2049 |
+
"grad_norm": 16.39994515518987,
|
| 2050 |
+
"learning_rate": 6.017128337832911e-07,
|
| 2051 |
+
"loss": 1.7061,
|
| 2052 |
+
"step": 2860
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.8613445378151261,
|
| 2056 |
+
"grad_norm": 9.64235814802451,
|
| 2057 |
+
"learning_rate": 5.770353923488775e-07,
|
| 2058 |
+
"loss": 1.8149,
|
| 2059 |
+
"step": 2870
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.8643457382953181,
|
| 2063 |
+
"grad_norm": 9.731437069326958,
|
| 2064 |
+
"learning_rate": 5.528436261712111e-07,
|
| 2065 |
+
"loss": 2.0985,
|
| 2066 |
+
"step": 2880
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.8673469387755102,
|
| 2070 |
+
"grad_norm": 10.203971652063059,
|
| 2071 |
+
"learning_rate": 5.291401916907768e-07,
|
| 2072 |
+
"loss": 1.7555,
|
| 2073 |
+
"step": 2890
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.8703481392557023,
|
| 2077 |
+
"grad_norm": 7.601026898998802,
|
| 2078 |
+
"learning_rate": 5.059276917255151e-07,
|
| 2079 |
+
"loss": 1.6832,
|
| 2080 |
+
"step": 2900
|
| 2081 |
+
}
|
| 2082 |
+
],
|
| 2083 |
+
"logging_steps": 10,
|
| 2084 |
+
"max_steps": 3332,
|
| 2085 |
+
"num_input_tokens_seen": 0,
|
| 2086 |
+
"num_train_epochs": 1,
|
| 2087 |
+
"save_steps": 100,
|
| 2088 |
+
"stateful_callbacks": {
|
| 2089 |
+
"TrainerControl": {
|
| 2090 |
+
"args": {
|
| 2091 |
+
"should_epoch_stop": false,
|
| 2092 |
+
"should_evaluate": false,
|
| 2093 |
+
"should_log": false,
|
| 2094 |
+
"should_save": true,
|
| 2095 |
+
"should_training_stop": false
|
| 2096 |
+
},
|
| 2097 |
+
"attributes": {}
|
| 2098 |
+
}
|
| 2099 |
+
},
|
| 2100 |
+
"total_flos": 3356272558080.0,
|
| 2101 |
+
"train_batch_size": 2,
|
| 2102 |
+
"trial_name": null,
|
| 2103 |
+
"trial_params": null
|
| 2104 |
+
}
|
checkpoint-2900/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3100/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-3100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3200/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-3300/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-3332/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-600/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
100257
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 100277,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-600/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-700/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100257,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "olmo2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 16,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"pad_token_id": 100277,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.57.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 100352
|
| 27 |
+
}
|