Upload folder using huggingface_hub
Browse files- base/49_128_e3_3e-5/adapter_config.json +39 -0
- base/49_128_e3_3e-5/adapter_model.safetensors +3 -0
- base/49_128_e3_3e-5/all_results.json +9 -0
- base/49_128_e3_3e-5/config.json +32 -0
- base/49_128_e3_3e-5/merges.txt +0 -0
- base/49_128_e3_3e-5/special_tokens_map.json +45 -0
- base/49_128_e3_3e-5/tokenizer.json +0 -0
- base/49_128_e3_3e-5/tokenizer_config.json +188 -0
- base/49_128_e3_3e-5/train_results.json +9 -0
- base/49_128_e3_3e-5/trainer_state.json +456 -0
- base/49_128_e3_3e-5/training_args.bin +3 -0
- base/49_128_e3_3e-5/vocab.json +0 -0
base/49_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
base/49_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94281ee14580375f8701c32b62fbe180036019034c230dd21a23ad6fca2c9b54
|
| 3 |
+
size 791751704
|
base/49_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.614012279428219e+17,
|
| 4 |
+
"train_loss": 0.7914719922775372,
|
| 5 |
+
"train_runtime": 264.6297,
|
| 6 |
+
"train_samples": 3156,
|
| 7 |
+
"train_samples_per_second": 35.778,
|
| 8 |
+
"train_steps_per_second": 1.122
|
| 9 |
+
}
|
base/49_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
base/49_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
base/49_128_e3_3e-5/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<reponame>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
base/49_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
base/49_128_e3_3e-5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"extra_special_tokens": {},
|
| 182 |
+
"model_max_length": 8192,
|
| 183 |
+
"pad_token": "<reponame>",
|
| 184 |
+
"padding_side": "left",
|
| 185 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 186 |
+
"unk_token": "<|endoftext|>",
|
| 187 |
+
"vocab_size": 49152
|
| 188 |
+
}
|
base/49_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.614012279428219e+17,
|
| 4 |
+
"train_loss": 0.7914719922775372,
|
| 5 |
+
"train_runtime": 264.6297,
|
| 6 |
+
"train_samples": 3156,
|
| 7 |
+
"train_samples_per_second": 35.778,
|
| 8 |
+
"train_steps_per_second": 1.122
|
| 9 |
+
}
|
base/49_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,456 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 297,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.050505050505050504,
|
| 14 |
+
"grad_norm": 0.6543053984642029,
|
| 15 |
+
"learning_rate": 4e-06,
|
| 16 |
+
"loss": 1.9666,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.10101010101010101,
|
| 21 |
+
"grad_norm": 0.614926815032959,
|
| 22 |
+
"learning_rate": 9e-06,
|
| 23 |
+
"loss": 1.9356,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.15151515151515152,
|
| 28 |
+
"grad_norm": 0.4947691261768341,
|
| 29 |
+
"learning_rate": 1.4e-05,
|
| 30 |
+
"loss": 1.8669,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.20202020202020202,
|
| 35 |
+
"grad_norm": 0.4939548671245575,
|
| 36 |
+
"learning_rate": 1.9e-05,
|
| 37 |
+
"loss": 1.8771,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.25252525252525254,
|
| 42 |
+
"grad_norm": 0.46868839859962463,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 1.8521,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.30303030303030304,
|
| 49 |
+
"grad_norm": 0.48774003982543945,
|
| 50 |
+
"learning_rate": 2.9e-05,
|
| 51 |
+
"loss": 1.7958,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.35353535353535354,
|
| 56 |
+
"grad_norm": 0.5537539124488831,
|
| 57 |
+
"learning_rate": 2.998338966852224e-05,
|
| 58 |
+
"loss": 1.7834,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.40404040404040403,
|
| 63 |
+
"grad_norm": 0.585176408290863,
|
| 64 |
+
"learning_rate": 2.991597324011973e-05,
|
| 65 |
+
"loss": 1.6669,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.45454545454545453,
|
| 70 |
+
"grad_norm": 0.563834011554718,
|
| 71 |
+
"learning_rate": 2.979694565876292e-05,
|
| 72 |
+
"loss": 1.6237,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5050505050505051,
|
| 77 |
+
"grad_norm": 0.6718980073928833,
|
| 78 |
+
"learning_rate": 2.96267187749297e-05,
|
| 79 |
+
"loss": 1.5887,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5555555555555556,
|
| 84 |
+
"grad_norm": 0.7574952840805054,
|
| 85 |
+
"learning_rate": 2.940588159515669e-05,
|
| 86 |
+
"loss": 1.5014,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6060606060606061,
|
| 91 |
+
"grad_norm": 0.8723017573356628,
|
| 92 |
+
"learning_rate": 2.913519824400216e-05,
|
| 93 |
+
"loss": 1.4119,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6565656565656566,
|
| 98 |
+
"grad_norm": 0.9389759302139282,
|
| 99 |
+
"learning_rate": 2.8815605320078453e-05,
|
| 100 |
+
"loss": 1.3711,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.7070707070707071,
|
| 105 |
+
"grad_norm": 1.1775588989257812,
|
| 106 |
+
"learning_rate": 2.8448208655302427e-05,
|
| 107 |
+
"loss": 1.286,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.7575757575757576,
|
| 112 |
+
"grad_norm": 1.3062646389007568,
|
| 113 |
+
"learning_rate": 2.80342794885772e-05,
|
| 114 |
+
"loss": 1.2257,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.8080808080808081,
|
| 119 |
+
"grad_norm": 1.049756407737732,
|
| 120 |
+
"learning_rate": 2.757525006714484e-05,
|
| 121 |
+
"loss": 1.1476,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.8585858585858586,
|
| 126 |
+
"grad_norm": 1.3888734579086304,
|
| 127 |
+
"learning_rate": 2.7072708690829888e-05,
|
| 128 |
+
"loss": 1.1799,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.9090909090909091,
|
| 133 |
+
"grad_norm": 1.2296152114868164,
|
| 134 |
+
"learning_rate": 2.6528394216321165e-05,
|
| 135 |
+
"loss": 1.0664,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.9595959595959596,
|
| 140 |
+
"grad_norm": 1.2978057861328125,
|
| 141 |
+
"learning_rate": 2.5944190040507823e-05,
|
| 142 |
+
"loss": 1.0181,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.0101010101010102,
|
| 147 |
+
"grad_norm": 1.268775224685669,
|
| 148 |
+
"learning_rate": 2.532211758368803e-05,
|
| 149 |
+
"loss": 0.9464,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.0606060606060606,
|
| 154 |
+
"grad_norm": 1.366642951965332,
|
| 155 |
+
"learning_rate": 2.4664329295199198e-05,
|
| 156 |
+
"loss": 0.8795,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.1111111111111112,
|
| 161 |
+
"grad_norm": 1.5060722827911377,
|
| 162 |
+
"learning_rate": 2.397310120567119e-05,
|
| 163 |
+
"loss": 0.7891,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.1616161616161615,
|
| 168 |
+
"grad_norm": 1.7605682611465454,
|
| 169 |
+
"learning_rate": 2.325082505167262e-05,
|
| 170 |
+
"loss": 0.7832,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.2121212121212122,
|
| 175 |
+
"grad_norm": 1.6712138652801514,
|
| 176 |
+
"learning_rate": 2.25e-05,
|
| 177 |
+
"loss": 0.7456,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.2626262626262625,
|
| 182 |
+
"grad_norm": 1.710675597190857,
|
| 183 |
+
"learning_rate": 2.1723224000244682e-05,
|
| 184 |
+
"loss": 0.7184,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.3131313131313131,
|
| 189 |
+
"grad_norm": 1.6852778196334839,
|
| 190 |
+
"learning_rate": 2.092318479555887e-05,
|
| 191 |
+
"loss": 0.6984,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.3636363636363638,
|
| 196 |
+
"grad_norm": 1.7866144180297852,
|
| 197 |
+
"learning_rate": 2.0102650622724555e-05,
|
| 198 |
+
"loss": 0.6789,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.4141414141414141,
|
| 203 |
+
"grad_norm": 1.84363853931427,
|
| 204 |
+
"learning_rate": 1.9264460633704307e-05,
|
| 205 |
+
"loss": 0.6679,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.4646464646464645,
|
| 210 |
+
"grad_norm": 1.7641829252243042,
|
| 211 |
+
"learning_rate": 1.84115150718166e-05,
|
| 212 |
+
"loss": 0.6235,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.5151515151515151,
|
| 217 |
+
"grad_norm": 2.0742874145507812,
|
| 218 |
+
"learning_rate": 1.754676523652728e-05,
|
| 219 |
+
"loss": 0.5703,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.5656565656565657,
|
| 224 |
+
"grad_norm": 1.8712676763534546,
|
| 225 |
+
"learning_rate": 1.667320327158037e-05,
|
| 226 |
+
"loss": 0.5703,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.6161616161616161,
|
| 231 |
+
"grad_norm": 1.701623558998108,
|
| 232 |
+
"learning_rate": 1.5793851811802445e-05,
|
| 233 |
+
"loss": 0.5657,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.6666666666666665,
|
| 238 |
+
"grad_norm": 2.07145357131958,
|
| 239 |
+
"learning_rate": 1.4911753524404069e-05,
|
| 240 |
+
"loss": 0.5244,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.7171717171717171,
|
| 245 |
+
"grad_norm": 1.793331503868103,
|
| 246 |
+
"learning_rate": 1.4029960580966573e-05,
|
| 247 |
+
"loss": 0.5104,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.7676767676767677,
|
| 252 |
+
"grad_norm": 2.3345186710357666,
|
| 253 |
+
"learning_rate": 1.3151524096542622e-05,
|
| 254 |
+
"loss": 0.4879,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.8181818181818183,
|
| 259 |
+
"grad_norm": 1.9282476902008057,
|
| 260 |
+
"learning_rate": 1.227948357241236e-05,
|
| 261 |
+
"loss": 0.4916,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.8686868686868687,
|
| 266 |
+
"grad_norm": 1.9456874132156372,
|
| 267 |
+
"learning_rate": 1.1416856379024835e-05,
|
| 268 |
+
"loss": 0.4676,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.9191919191919191,
|
| 273 |
+
"grad_norm": 1.6293978691101074,
|
| 274 |
+
"learning_rate": 1.056662731551474e-05,
|
| 275 |
+
"loss": 0.4285,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.9696969696969697,
|
| 280 |
+
"grad_norm": 1.8693084716796875,
|
| 281 |
+
"learning_rate": 9.731738281920162e-06,
|
| 282 |
+
"loss": 0.413,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.0202020202020203,
|
| 287 |
+
"grad_norm": 1.9546136856079102,
|
| 288 |
+
"learning_rate": 8.915078099836506e-06,
|
| 289 |
+
"loss": 0.3626,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.0707070707070705,
|
| 294 |
+
"grad_norm": 2.0389304161071777,
|
| 295 |
+
"learning_rate": 8.11947251672864e-06,
|
| 296 |
+
"loss": 0.3179,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.121212121212121,
|
| 301 |
+
"grad_norm": 2.1795268058776855,
|
| 302 |
+
"learning_rate": 7.3476744284874446e-06,
|
| 303 |
+
"loss": 0.299,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.1717171717171717,
|
| 308 |
+
"grad_norm": 1.8628838062286377,
|
| 309 |
+
"learning_rate": 6.602354354062003e-06,
|
| 310 |
+
"loss": 0.3003,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.2222222222222223,
|
| 315 |
+
"grad_norm": 2.112964153289795,
|
| 316 |
+
"learning_rate": 5.8860911951265186e-06,
|
| 317 |
+
"loss": 0.2679,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.2727272727272725,
|
| 322 |
+
"grad_norm": 1.6593751907348633,
|
| 323 |
+
"learning_rate": 5.201363312754458e-06,
|
| 324 |
+
"loss": 0.2788,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.323232323232323,
|
| 329 |
+
"grad_norm": 1.8782399892807007,
|
| 330 |
+
"learning_rate": 4.550539951975996e-06,
|
| 331 |
+
"loss": 0.284,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.3737373737373737,
|
| 336 |
+
"grad_norm": 1.7790881395339966,
|
| 337 |
+
"learning_rate": 3.9358730438906675e-06,
|
| 338 |
+
"loss": 0.2513,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.4242424242424243,
|
| 343 |
+
"grad_norm": 1.9162936210632324,
|
| 344 |
+
"learning_rate": 3.3594894137011207e-06,
|
| 345 |
+
"loss": 0.2423,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.474747474747475,
|
| 350 |
+
"grad_norm": 1.6140774488449097,
|
| 351 |
+
"learning_rate": 2.8233834216290637e-06,
|
| 352 |
+
"loss": 0.2565,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.525252525252525,
|
| 357 |
+
"grad_norm": 1.7328420877456665,
|
| 358 |
+
"learning_rate": 2.329410062176771e-06,
|
| 359 |
+
"loss": 0.2552,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.5757575757575757,
|
| 364 |
+
"grad_norm": 1.564235806465149,
|
| 365 |
+
"learning_rate": 1.8792785456116257e-06,
|
| 366 |
+
"loss": 0.2348,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.6262626262626263,
|
| 371 |
+
"grad_norm": 1.6609153747558594,
|
| 372 |
+
"learning_rate": 1.474546383882534e-06,
|
| 373 |
+
"loss": 0.2262,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.676767676767677,
|
| 378 |
+
"grad_norm": 1.4131369590759277,
|
| 379 |
+
"learning_rate": 1.116614001431685e-06,
|
| 380 |
+
"loss": 0.2467,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.7272727272727275,
|
| 385 |
+
"grad_norm": 1.3170446157455444,
|
| 386 |
+
"learning_rate": 8.06719889548957e-07,
|
| 387 |
+
"loss": 0.2188,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.7777777777777777,
|
| 392 |
+
"grad_norm": 1.3941270112991333,
|
| 393 |
+
"learning_rate": 5.459363210354984e-07,
|
| 394 |
+
"loss": 0.2208,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.8282828282828283,
|
| 399 |
+
"grad_norm": 1.4964709281921387,
|
| 400 |
+
"learning_rate": 3.3516564000428404e-07,
|
| 401 |
+
"loss": 0.219,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.878787878787879,
|
| 406 |
+
"grad_norm": 1.40897536277771,
|
| 407 |
+
"learning_rate": 1.7513713965542244e-07,
|
| 408 |
+
"loss": 0.2468,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.929292929292929,
|
| 413 |
+
"grad_norm": 1.5261189937591553,
|
| 414 |
+
"learning_rate": 6.64045388294826e-08,
|
| 415 |
+
"loss": 0.2084,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.9797979797979797,
|
| 420 |
+
"grad_norm": 1.4547865390777588,
|
| 421 |
+
"learning_rate": 9.344066070327007e-09,
|
| 422 |
+
"loss": 0.2377,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.0,
|
| 427 |
+
"step": 297,
|
| 428 |
+
"total_flos": 5.614012279428219e+17,
|
| 429 |
+
"train_loss": 0.7914719922775372,
|
| 430 |
+
"train_runtime": 264.6297,
|
| 431 |
+
"train_samples_per_second": 35.778,
|
| 432 |
+
"train_steps_per_second": 1.122
|
| 433 |
+
}
|
| 434 |
+
],
|
| 435 |
+
"logging_steps": 5,
|
| 436 |
+
"max_steps": 297,
|
| 437 |
+
"num_input_tokens_seen": 0,
|
| 438 |
+
"num_train_epochs": 3,
|
| 439 |
+
"save_steps": 500,
|
| 440 |
+
"stateful_callbacks": {
|
| 441 |
+
"TrainerControl": {
|
| 442 |
+
"args": {
|
| 443 |
+
"should_epoch_stop": false,
|
| 444 |
+
"should_evaluate": false,
|
| 445 |
+
"should_log": false,
|
| 446 |
+
"should_save": false,
|
| 447 |
+
"should_training_stop": false
|
| 448 |
+
},
|
| 449 |
+
"attributes": {}
|
| 450 |
+
}
|
| 451 |
+
},
|
| 452 |
+
"total_flos": 5.614012279428219e+17,
|
| 453 |
+
"train_batch_size": 2,
|
| 454 |
+
"trial_name": null,
|
| 455 |
+
"trial_params": null
|
| 456 |
+
}
|
base/49_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3fdff96283821bf6806776e76db143e83cc1336002545c7c056210085a7784b
|
| 3 |
+
size 8017
|
base/49_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|