Upload folder using huggingface_hub
Browse files- base/54_128_e3_3e-5/adapter_config.json +39 -0
- base/54_128_e3_3e-5/adapter_model.safetensors +3 -0
- base/54_128_e3_3e-5/all_results.json +9 -0
- base/54_128_e3_3e-5/config.json +32 -0
- base/54_128_e3_3e-5/merges.txt +0 -0
- base/54_128_e3_3e-5/special_tokens_map.json +45 -0
- base/54_128_e3_3e-5/tokenizer.json +0 -0
- base/54_128_e3_3e-5/tokenizer_config.json +188 -0
- base/54_128_e3_3e-5/train_results.json +9 -0
- base/54_128_e3_3e-5/trainer_state.json +463 -0
- base/54_128_e3_3e-5/training_args.bin +3 -0
- base/54_128_e3_3e-5/vocab.json +0 -0
base/54_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 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
base/54_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ffabf95531d69b42246ba283fbbef68b56a8856269bdcddd15a45fc6b792224
|
| 3 |
+
size 791751704
|
base/54_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.940994678760407e+17,
|
| 4 |
+
"train_loss": 0.8012670471329894,
|
| 5 |
+
"train_runtime": 282.1745,
|
| 6 |
+
"train_samples": 3224,
|
| 7 |
+
"train_samples_per_second": 34.277,
|
| 8 |
+
"train_steps_per_second": 1.074
|
| 9 |
+
}
|
base/54_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/54_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
base/54_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/54_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
base/54_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/54_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.940994678760407e+17,
|
| 4 |
+
"train_loss": 0.8012670471329894,
|
| 5 |
+
"train_runtime": 282.1745,
|
| 6 |
+
"train_samples": 3224,
|
| 7 |
+
"train_samples_per_second": 34.277,
|
| 8 |
+
"train_steps_per_second": 1.074
|
| 9 |
+
}
|
base/54_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,463 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 303,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04950495049504951,
|
| 14 |
+
"grad_norm": 0.7119670510292053,
|
| 15 |
+
"learning_rate": 3.870967741935484e-06,
|
| 16 |
+
"loss": 1.9766,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09900990099009901,
|
| 21 |
+
"grad_norm": 0.5174402594566345,
|
| 22 |
+
"learning_rate": 8.70967741935484e-06,
|
| 23 |
+
"loss": 1.9583,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1485148514851485,
|
| 28 |
+
"grad_norm": 0.5573070645332336,
|
| 29 |
+
"learning_rate": 1.3548387096774194e-05,
|
| 30 |
+
"loss": 1.9696,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.19801980198019803,
|
| 35 |
+
"grad_norm": 0.4669293761253357,
|
| 36 |
+
"learning_rate": 1.838709677419355e-05,
|
| 37 |
+
"loss": 1.9077,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24752475247524752,
|
| 42 |
+
"grad_norm": 0.5369893312454224,
|
| 43 |
+
"learning_rate": 2.3225806451612902e-05,
|
| 44 |
+
"loss": 1.8624,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.297029702970297,
|
| 49 |
+
"grad_norm": 0.49319079518318176,
|
| 50 |
+
"learning_rate": 2.806451612903226e-05,
|
| 51 |
+
"loss": 1.8046,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3465346534653465,
|
| 56 |
+
"grad_norm": 0.6555143594741821,
|
| 57 |
+
"learning_rate": 2.999099627425303e-05,
|
| 58 |
+
"loss": 1.7479,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.39603960396039606,
|
| 63 |
+
"grad_norm": 0.5682657957077026,
|
| 64 |
+
"learning_rate": 2.9936012644425518e-05,
|
| 65 |
+
"loss": 1.6574,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.44554455445544555,
|
| 70 |
+
"grad_norm": 0.6389867663383484,
|
| 71 |
+
"learning_rate": 2.9831230554218908e-05,
|
| 72 |
+
"loss": 1.6748,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.49504950495049505,
|
| 77 |
+
"grad_norm": 0.6430660486221313,
|
| 78 |
+
"learning_rate": 2.9676999359709137e-05,
|
| 79 |
+
"loss": 1.5594,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5445544554455446,
|
| 84 |
+
"grad_norm": 0.9339398741722107,
|
| 85 |
+
"learning_rate": 2.947383328622607e-05,
|
| 86 |
+
"loss": 1.5164,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.594059405940594,
|
| 91 |
+
"grad_norm": 0.926177442073822,
|
| 92 |
+
"learning_rate": 2.922240971386449e-05,
|
| 93 |
+
"loss": 1.4744,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6435643564356436,
|
| 98 |
+
"grad_norm": 0.9308810830116272,
|
| 99 |
+
"learning_rate": 2.8923566919017475e-05,
|
| 100 |
+
"loss": 1.3739,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.693069306930693,
|
| 105 |
+
"grad_norm": 1.0380762815475464,
|
| 106 |
+
"learning_rate": 2.8578301279462227e-05,
|
| 107 |
+
"loss": 1.3238,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.7425742574257426,
|
| 112 |
+
"grad_norm": 1.0957621335983276,
|
| 113 |
+
"learning_rate": 2.818776395231685e-05,
|
| 114 |
+
"loss": 1.2472,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.7920792079207921,
|
| 119 |
+
"grad_norm": 1.3891359567642212,
|
| 120 |
+
"learning_rate": 2.7753257035944216e-05,
|
| 121 |
+
"loss": 1.1738,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.8415841584158416,
|
| 126 |
+
"grad_norm": 1.4095536470413208,
|
| 127 |
+
"learning_rate": 2.727622922859965e-05,
|
| 128 |
+
"loss": 1.1338,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.8910891089108911,
|
| 133 |
+
"grad_norm": 1.3054324388504028,
|
| 134 |
+
"learning_rate": 2.6758270998296906e-05,
|
| 135 |
+
"loss": 1.1139,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.9405940594059405,
|
| 140 |
+
"grad_norm": 1.5511865615844727,
|
| 141 |
+
"learning_rate": 2.6201109279996712e-05,
|
| 142 |
+
"loss": 1.0794,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.9900990099009901,
|
| 147 |
+
"grad_norm": 2.0087814331054688,
|
| 148 |
+
"learning_rate": 2.5606601717798212e-05,
|
| 149 |
+
"loss": 0.9833,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.0396039603960396,
|
| 154 |
+
"grad_norm": 1.640615701675415,
|
| 155 |
+
"learning_rate": 2.497673047133035e-05,
|
| 156 |
+
"loss": 0.8922,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.0891089108910892,
|
| 161 |
+
"grad_norm": 1.4243311882019043,
|
| 162 |
+
"learning_rate": 2.431359560699357e-05,
|
| 163 |
+
"loss": 0.8481,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.1386138613861387,
|
| 168 |
+
"grad_norm": 1.4991133213043213,
|
| 169 |
+
"learning_rate": 2.361940809608616e-05,
|
| 170 |
+
"loss": 0.8159,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.188118811881188,
|
| 175 |
+
"grad_norm": 1.8631993532180786,
|
| 176 |
+
"learning_rate": 2.2896482443160337e-05,
|
| 177 |
+
"loss": 0.8032,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.2376237623762376,
|
| 182 |
+
"grad_norm": 1.440885066986084,
|
| 183 |
+
"learning_rate": 2.214722896918606e-05,
|
| 184 |
+
"loss": 0.7477,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.2871287128712872,
|
| 189 |
+
"grad_norm": 1.6624423265457153,
|
| 190 |
+
"learning_rate": 2.1374145775251332e-05,
|
| 191 |
+
"loss": 0.7302,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.3366336633663367,
|
| 196 |
+
"grad_norm": 1.9620729684829712,
|
| 197 |
+
"learning_rate": 2.0579810413593116e-05,
|
| 198 |
+
"loss": 0.7279,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.386138613861386,
|
| 203 |
+
"grad_norm": 1.9532698392868042,
|
| 204 |
+
"learning_rate": 1.9766871293728525e-05,
|
| 205 |
+
"loss": 0.679,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.4356435643564356,
|
| 210 |
+
"grad_norm": 1.7674474716186523,
|
| 211 |
+
"learning_rate": 1.893803885233936e-05,
|
| 212 |
+
"loss": 0.6496,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.4851485148514851,
|
| 217 |
+
"grad_norm": 1.9492448568344116,
|
| 218 |
+
"learning_rate": 1.8096076516350596e-05,
|
| 219 |
+
"loss": 0.6111,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.5346534653465347,
|
| 224 |
+
"grad_norm": 2.013254404067993,
|
| 225 |
+
"learning_rate": 1.7243791489333066e-05,
|
| 226 |
+
"loss": 0.634,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.5841584158415842,
|
| 231 |
+
"grad_norm": 1.95407235622406,
|
| 232 |
+
"learning_rate": 1.638402539194953e-05,
|
| 233 |
+
"loss": 0.5712,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.6336633663366338,
|
| 238 |
+
"grad_norm": 1.9810817241668701,
|
| 239 |
+
"learning_rate": 1.551964478765003e-05,
|
| 240 |
+
"loss": 0.5853,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.6831683168316833,
|
| 245 |
+
"grad_norm": 1.856523036956787,
|
| 246 |
+
"learning_rate": 1.4653531625204986e-05,
|
| 247 |
+
"loss": 0.531,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.7326732673267327,
|
| 252 |
+
"grad_norm": 1.9325554370880127,
|
| 253 |
+
"learning_rate": 1.3788573629941811e-05,
|
| 254 |
+
"loss": 0.4632,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.7821782178217822,
|
| 259 |
+
"grad_norm": 1.898939847946167,
|
| 260 |
+
"learning_rate": 1.2927654675721771e-05,
|
| 261 |
+
"loss": 0.5131,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.8316831683168315,
|
| 266 |
+
"grad_norm": 2.0521693229675293,
|
| 267 |
+
"learning_rate": 1.2073645169758078e-05,
|
| 268 |
+
"loss": 0.4561,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.881188118811881,
|
| 273 |
+
"grad_norm": 2.640407085418701,
|
| 274 |
+
"learning_rate": 1.122939248233346e-05,
|
| 275 |
+
"loss": 0.4377,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.9306930693069306,
|
| 280 |
+
"grad_norm": 1.9293057918548584,
|
| 281 |
+
"learning_rate": 1.0397711453325574e-05,
|
| 282 |
+
"loss": 0.4411,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.9801980198019802,
|
| 287 |
+
"grad_norm": 2.047621488571167,
|
| 288 |
+
"learning_rate": 9.581375007192707e-06,
|
| 289 |
+
"loss": 0.4175,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.0297029702970297,
|
| 294 |
+
"grad_norm": 1.833793044090271,
|
| 295 |
+
"learning_rate": 8.783104907710549e-06,
|
| 296 |
+
"loss": 0.3386,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.0792079207920793,
|
| 301 |
+
"grad_norm": 2.0424859523773193,
|
| 302 |
+
"learning_rate": 8.005562683284778e-06,
|
| 303 |
+
"loss": 0.2997,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.128712871287129,
|
| 308 |
+
"grad_norm": 1.7203387022018433,
|
| 309 |
+
"learning_rate": 7.251340753095676e-06,
|
| 310 |
+
"loss": 0.297,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.1782178217821784,
|
| 315 |
+
"grad_norm": 1.8412830829620361,
|
| 316 |
+
"learning_rate": 6.522953783661122e-06,
|
| 317 |
+
"loss": 0.3237,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.227722772277228,
|
| 322 |
+
"grad_norm": 1.899208426475525,
|
| 323 |
+
"learning_rate": 5.822830304636347e-06,
|
| 324 |
+
"loss": 0.2953,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.2772277227722775,
|
| 329 |
+
"grad_norm": 1.7738488912582397,
|
| 330 |
+
"learning_rate": 5.153304611804362e-06,
|
| 331 |
+
"loss": 0.3013,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.3267326732673266,
|
| 336 |
+
"grad_norm": 1.6585019826889038,
|
| 337 |
+
"learning_rate": 4.516608984253359e-06,
|
| 338 |
+
"loss": 0.2624,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.376237623762376,
|
| 343 |
+
"grad_norm": 1.8295166492462158,
|
| 344 |
+
"learning_rate": 3.914866241690115e-06,
|
| 345 |
+
"loss": 0.279,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.4257425742574257,
|
| 350 |
+
"grad_norm": 1.8832124471664429,
|
| 351 |
+
"learning_rate": 3.3500826667040478e-06,
|
| 352 |
+
"loss": 0.2652,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.4752475247524752,
|
| 357 |
+
"grad_norm": 1.6764395236968994,
|
| 358 |
+
"learning_rate": 2.8241413155800814e-06,
|
| 359 |
+
"loss": 0.267,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.5247524752475248,
|
| 364 |
+
"grad_norm": 1.7070584297180176,
|
| 365 |
+
"learning_rate": 2.3387957399627697e-06,
|
| 366 |
+
"loss": 0.2402,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.5742574257425743,
|
| 371 |
+
"grad_norm": 1.9102427959442139,
|
| 372 |
+
"learning_rate": 1.8956641403044578e-06,
|
| 373 |
+
"loss": 0.2354,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.623762376237624,
|
| 378 |
+
"grad_norm": 1.8111540079116821,
|
| 379 |
+
"learning_rate": 1.4962239705906072e-06,
|
| 380 |
+
"loss": 0.2351,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.6732673267326734,
|
| 385 |
+
"grad_norm": 1.5645720958709717,
|
| 386 |
+
"learning_rate": 1.1418070123306989e-06,
|
| 387 |
+
"loss": 0.2317,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.7227722772277225,
|
| 392 |
+
"grad_norm": 1.7960097789764404,
|
| 393 |
+
"learning_rate": 8.335949342387217e-07,
|
| 394 |
+
"loss": 0.2303,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.772277227722772,
|
| 399 |
+
"grad_norm": 1.5213086605072021,
|
| 400 |
+
"learning_rate": 5.726153524077144e-07,
|
| 401 |
+
"loss": 0.2373,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.8217821782178216,
|
| 406 |
+
"grad_norm": 1.5130654573440552,
|
| 407 |
+
"learning_rate": 3.597384041142654e-07,
|
| 408 |
+
"loss": 0.2429,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.871287128712871,
|
| 413 |
+
"grad_norm": 1.4772449731826782,
|
| 414 |
+
"learning_rate": 1.9567384667631637e-07,
|
| 415 |
+
"loss": 0.2443,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.9207920792079207,
|
| 420 |
+
"grad_norm": 1.6653465032577515,
|
| 421 |
+
"learning_rate": 8.096869103699056e-08,
|
| 422 |
+
"loss": 0.2403,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.9702970297029703,
|
| 427 |
+
"grad_norm": 1.6397658586502075,
|
| 428 |
+
"learning_rate": 1.6005377964413702e-08,
|
| 429 |
+
"loss": 0.2478,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 3.0,
|
| 434 |
+
"step": 303,
|
| 435 |
+
"total_flos": 5.940994678760407e+17,
|
| 436 |
+
"train_loss": 0.8012670471329894,
|
| 437 |
+
"train_runtime": 282.1745,
|
| 438 |
+
"train_samples_per_second": 34.277,
|
| 439 |
+
"train_steps_per_second": 1.074
|
| 440 |
+
}
|
| 441 |
+
],
|
| 442 |
+
"logging_steps": 5,
|
| 443 |
+
"max_steps": 303,
|
| 444 |
+
"num_input_tokens_seen": 0,
|
| 445 |
+
"num_train_epochs": 3,
|
| 446 |
+
"save_steps": 500,
|
| 447 |
+
"stateful_callbacks": {
|
| 448 |
+
"TrainerControl": {
|
| 449 |
+
"args": {
|
| 450 |
+
"should_epoch_stop": false,
|
| 451 |
+
"should_evaluate": false,
|
| 452 |
+
"should_log": false,
|
| 453 |
+
"should_save": false,
|
| 454 |
+
"should_training_stop": false
|
| 455 |
+
},
|
| 456 |
+
"attributes": {}
|
| 457 |
+
}
|
| 458 |
+
},
|
| 459 |
+
"total_flos": 5.940994678760407e+17,
|
| 460 |
+
"train_batch_size": 2,
|
| 461 |
+
"trial_name": null,
|
| 462 |
+
"trial_params": null
|
| 463 |
+
}
|
base/54_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c13c6279463a1538dab500e10bc0bd7a2d43e528e2d567dceea2a67fdb0f8f4f
|
| 3 |
+
size 8017
|
base/54_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|