Upload folder using huggingface_hub
Browse files- 117_128_e3_3e-5/adapter_config.json +39 -0
- 117_128_e3_3e-5/adapter_model.safetensors +3 -0
- 117_128_e3_3e-5/all_results.json +9 -0
- 117_128_e3_3e-5/config.json +32 -0
- 117_128_e3_3e-5/merges.txt +0 -0
- 117_128_e3_3e-5/special_tokens_map.json +45 -0
- 117_128_e3_3e-5/tokenizer.json +0 -0
- 117_128_e3_3e-5/tokenizer_config.json +188 -0
- 117_128_e3_3e-5/train_results.json +9 -0
- 117_128_e3_3e-5/trainer_state.json +659 -0
- 117_128_e3_3e-5/training_args.bin +3 -0
- 117_128_e3_3e-5/vocab.json +0 -0
117_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 |
+
"o_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
117_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:958118c66c5df5de71fb5e4433244e245e13cccf77715575936ed8ee9b2e2a5d
|
| 3 |
+
size 791751704
|
117_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.711067727737651e+17,
|
| 4 |
+
"train_loss": 0.4041794179653635,
|
| 5 |
+
"train_runtime": 261.1891,
|
| 6 |
+
"train_samples": 4694,
|
| 7 |
+
"train_samples_per_second": 53.915,
|
| 8 |
+
"train_steps_per_second": 1.688
|
| 9 |
+
}
|
117_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 |
+
}
|
117_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
117_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 |
+
}
|
117_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
117_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 |
+
}
|
117_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 5.711067727737651e+17,
|
| 4 |
+
"train_loss": 0.4041794179653635,
|
| 5 |
+
"train_runtime": 261.1891,
|
| 6 |
+
"train_samples": 4694,
|
| 7 |
+
"train_samples_per_second": 53.915,
|
| 8 |
+
"train_steps_per_second": 1.688
|
| 9 |
+
}
|
117_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,659 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 441,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034013605442176874,
|
| 14 |
+
"grad_norm": 0.7761524319648743,
|
| 15 |
+
"learning_rate": 5.2173913043478265e-06,
|
| 16 |
+
"loss": 1.4047,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06802721088435375,
|
| 21 |
+
"grad_norm": 0.6430684328079224,
|
| 22 |
+
"learning_rate": 1.173913043478261e-05,
|
| 23 |
+
"loss": 1.4044,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.10204081632653061,
|
| 28 |
+
"grad_norm": 0.7615648508071899,
|
| 29 |
+
"learning_rate": 1.8260869565217393e-05,
|
| 30 |
+
"loss": 1.3302,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1360544217687075,
|
| 35 |
+
"grad_norm": 0.6194230914115906,
|
| 36 |
+
"learning_rate": 2.4782608695652175e-05,
|
| 37 |
+
"loss": 1.2694,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17006802721088435,
|
| 42 |
+
"grad_norm": 0.6732345819473267,
|
| 43 |
+
"learning_rate": 2.9999576350789992e-05,
|
| 44 |
+
"loss": 1.2609,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.20408163265306123,
|
| 49 |
+
"grad_norm": 0.6071294546127319,
|
| 50 |
+
"learning_rate": 2.9984751140989417e-05,
|
| 51 |
+
"loss": 1.1422,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.23809523809523808,
|
| 56 |
+
"grad_norm": 0.5949280858039856,
|
| 57 |
+
"learning_rate": 2.994876739510005e-05,
|
| 58 |
+
"loss": 1.2455,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.272108843537415,
|
| 63 |
+
"grad_norm": 0.6747593879699707,
|
| 64 |
+
"learning_rate": 2.9891675922333125e-05,
|
| 65 |
+
"loss": 1.0714,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.30612244897959184,
|
| 70 |
+
"grad_norm": 0.579474151134491,
|
| 71 |
+
"learning_rate": 2.9813557336105277e-05,
|
| 72 |
+
"loss": 1.0749,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3401360544217687,
|
| 77 |
+
"grad_norm": 0.615601122379303,
|
| 78 |
+
"learning_rate": 2.971452194021204e-05,
|
| 79 |
+
"loss": 1.022,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3741496598639456,
|
| 84 |
+
"grad_norm": 0.6667152643203735,
|
| 85 |
+
"learning_rate": 2.9594709573078373e-05,
|
| 86 |
+
"loss": 1.0088,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.40816326530612246,
|
| 91 |
+
"grad_norm": 0.6944518089294434,
|
| 92 |
+
"learning_rate": 2.9454289410306202e-05,
|
| 93 |
+
"loss": 0.9762,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4421768707482993,
|
| 98 |
+
"grad_norm": 0.821300745010376,
|
| 99 |
+
"learning_rate": 2.929345972579768e-05,
|
| 100 |
+
"loss": 0.8948,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.47619047619047616,
|
| 105 |
+
"grad_norm": 0.8369089961051941,
|
| 106 |
+
"learning_rate": 2.9112447611791563e-05,
|
| 107 |
+
"loss": 0.9094,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5102040816326531,
|
| 112 |
+
"grad_norm": 0.8159622550010681,
|
| 113 |
+
"learning_rate": 2.8911508658207956e-05,
|
| 114 |
+
"loss": 0.8175,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.54421768707483,
|
| 119 |
+
"grad_norm": 0.8391682505607605,
|
| 120 |
+
"learning_rate": 2.8690926591754142e-05,
|
| 121 |
+
"loss": 0.8239,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5782312925170068,
|
| 126 |
+
"grad_norm": 0.9337536692619324,
|
| 127 |
+
"learning_rate": 2.8451012875301278e-05,
|
| 128 |
+
"loss": 0.7903,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6122448979591837,
|
| 133 |
+
"grad_norm": 0.9054645299911499,
|
| 134 |
+
"learning_rate": 2.8192106268097336e-05,
|
| 135 |
+
"loss": 0.7667,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6462585034013606,
|
| 140 |
+
"grad_norm": 0.9789870977401733,
|
| 141 |
+
"learning_rate": 2.7914572347437576e-05,
|
| 142 |
+
"loss": 0.7778,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6802721088435374,
|
| 147 |
+
"grad_norm": 1.0678824186325073,
|
| 148 |
+
"learning_rate": 2.7618802992467718e-05,
|
| 149 |
+
"loss": 0.6514,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7142857142857143,
|
| 154 |
+
"grad_norm": 1.0662013292312622,
|
| 155 |
+
"learning_rate": 2.7305215830848867e-05,
|
| 156 |
+
"loss": 0.5992,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7482993197278912,
|
| 161 |
+
"grad_norm": 1.1542693376541138,
|
| 162 |
+
"learning_rate": 2.697425364906534e-05,
|
| 163 |
+
"loss": 0.5688,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.782312925170068,
|
| 168 |
+
"grad_norm": 1.0753027200698853,
|
| 169 |
+
"learning_rate": 2.6626383767208166e-05,
|
| 170 |
+
"loss": 0.5393,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8163265306122449,
|
| 175 |
+
"grad_norm": 1.0218164920806885,
|
| 176 |
+
"learning_rate": 2.6262097379117015e-05,
|
| 177 |
+
"loss": 0.637,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8503401360544217,
|
| 182 |
+
"grad_norm": 1.2301396131515503,
|
| 183 |
+
"learning_rate": 2.588190885881229e-05,
|
| 184 |
+
"loss": 0.5118,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.8843537414965986,
|
| 189 |
+
"grad_norm": 1.10712468624115,
|
| 190 |
+
"learning_rate": 2.5486355034196686e-05,
|
| 191 |
+
"loss": 0.486,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9183673469387755,
|
| 196 |
+
"grad_norm": 1.1446400880813599,
|
| 197 |
+
"learning_rate": 2.5075994429051775e-05,
|
| 198 |
+
"loss": 0.5286,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9523809523809523,
|
| 203 |
+
"grad_norm": 1.1872553825378418,
|
| 204 |
+
"learning_rate": 2.465140647439991e-05,
|
| 205 |
+
"loss": 0.4879,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9863945578231292,
|
| 210 |
+
"grad_norm": 1.2186205387115479,
|
| 211 |
+
"learning_rate": 2.4213190690345018e-05,
|
| 212 |
+
"loss": 0.4585,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0204081632653061,
|
| 217 |
+
"grad_norm": 1.2183841466903687,
|
| 218 |
+
"learning_rate": 2.3761965839547515e-05,
|
| 219 |
+
"loss": 0.4162,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.054421768707483,
|
| 224 |
+
"grad_norm": 1.0857850313186646,
|
| 225 |
+
"learning_rate": 2.3298369053528632e-05,
|
| 226 |
+
"loss": 0.4001,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.08843537414966,
|
| 231 |
+
"grad_norm": 1.6746795177459717,
|
| 232 |
+
"learning_rate": 2.282305493303785e-05,
|
| 233 |
+
"loss": 0.3941,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1224489795918366,
|
| 238 |
+
"grad_norm": 1.0513867139816284,
|
| 239 |
+
"learning_rate": 2.233669462375368e-05,
|
| 240 |
+
"loss": 0.3248,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1564625850340136,
|
| 245 |
+
"grad_norm": 1.4389575719833374,
|
| 246 |
+
"learning_rate": 2.1839974868622956e-05,
|
| 247 |
+
"loss": 0.3668,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.1904761904761905,
|
| 252 |
+
"grad_norm": 1.1495342254638672,
|
| 253 |
+
"learning_rate": 2.1333597038176704e-05,
|
| 254 |
+
"loss": 0.2902,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2244897959183674,
|
| 259 |
+
"grad_norm": 1.2804063558578491,
|
| 260 |
+
"learning_rate": 2.081827614019177e-05,
|
| 261 |
+
"loss": 0.2808,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2585034013605443,
|
| 266 |
+
"grad_norm": 1.4058798551559448,
|
| 267 |
+
"learning_rate": 2.0294739810096657e-05,
|
| 268 |
+
"loss": 0.3341,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.2925170068027212,
|
| 273 |
+
"grad_norm": 1.5695240497589111,
|
| 274 |
+
"learning_rate": 1.976372728354699e-05,
|
| 275 |
+
"loss": 0.2757,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3265306122448979,
|
| 280 |
+
"grad_norm": 1.094007968902588,
|
| 281 |
+
"learning_rate": 1.9225988352621445e-05,
|
| 282 |
+
"loss": 0.2918,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3605442176870748,
|
| 287 |
+
"grad_norm": 1.497044563293457,
|
| 288 |
+
"learning_rate": 1.8682282307111988e-05,
|
| 289 |
+
"loss": 0.259,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.3945578231292517,
|
| 294 |
+
"grad_norm": 1.457971215248108,
|
| 295 |
+
"learning_rate": 1.8133376862403233e-05,
|
| 296 |
+
"loss": 0.2423,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4285714285714286,
|
| 301 |
+
"grad_norm": 1.2311850786209106,
|
| 302 |
+
"learning_rate": 1.7580047075454877e-05,
|
| 303 |
+
"loss": 0.2302,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4625850340136055,
|
| 308 |
+
"grad_norm": 1.1251230239868164,
|
| 309 |
+
"learning_rate": 1.702307425041779e-05,
|
| 310 |
+
"loss": 0.2677,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.4965986394557822,
|
| 315 |
+
"grad_norm": 1.1030064821243286,
|
| 316 |
+
"learning_rate": 1.646324483542902e-05,
|
| 317 |
+
"loss": 0.2233,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5306122448979593,
|
| 322 |
+
"grad_norm": 1.1362409591674805,
|
| 323 |
+
"learning_rate": 1.5901349312143503e-05,
|
| 324 |
+
"loss": 0.2137,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.564625850340136,
|
| 329 |
+
"grad_norm": 1.1852717399597168,
|
| 330 |
+
"learning_rate": 1.533818107957038e-05,
|
| 331 |
+
"loss": 0.2109,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.598639455782313,
|
| 336 |
+
"grad_norm": 1.1488208770751953,
|
| 337 |
+
"learning_rate": 1.4774535333790046e-05,
|
| 338 |
+
"loss": 0.235,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6326530612244898,
|
| 343 |
+
"grad_norm": 1.2795830965042114,
|
| 344 |
+
"learning_rate": 1.4211207945133685e-05,
|
| 345 |
+
"loss": 0.2336,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6666666666666665,
|
| 350 |
+
"grad_norm": 1.1346216201782227,
|
| 351 |
+
"learning_rate": 1.3648994334410798e-05,
|
| 352 |
+
"loss": 0.2021,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7006802721088436,
|
| 357 |
+
"grad_norm": 1.2687422037124634,
|
| 358 |
+
"learning_rate": 1.3088688349771425e-05,
|
| 359 |
+
"loss": 0.2161,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7346938775510203,
|
| 364 |
+
"grad_norm": 1.3018598556518555,
|
| 365 |
+
"learning_rate": 1.2531081145788989e-05,
|
| 366 |
+
"loss": 0.194,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.7687074829931972,
|
| 371 |
+
"grad_norm": 1.2137506008148193,
|
| 372 |
+
"learning_rate": 1.1976960066346474e-05,
|
| 373 |
+
"loss": 0.1664,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8027210884353742,
|
| 378 |
+
"grad_norm": 1.4094206094741821,
|
| 379 |
+
"learning_rate": 1.1427107532903298e-05,
|
| 380 |
+
"loss": 0.1551,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.836734693877551,
|
| 385 |
+
"grad_norm": 1.0904594659805298,
|
| 386 |
+
"learning_rate": 1.0882299939712727e-05,
|
| 387 |
+
"loss": 0.1619,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.870748299319728,
|
| 392 |
+
"grad_norm": 1.0567269325256348,
|
| 393 |
+
"learning_rate": 1.0343306557549662e-05,
|
| 394 |
+
"loss": 0.1634,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9047619047619047,
|
| 399 |
+
"grad_norm": 1.2228094339370728,
|
| 400 |
+
"learning_rate": 9.810888447496859e-06,
|
| 401 |
+
"loss": 0.1539,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.9387755102040818,
|
| 406 |
+
"grad_norm": 1.077606201171875,
|
| 407 |
+
"learning_rate": 9.285797386323237e-06,
|
| 408 |
+
"loss": 0.1369,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.9727891156462585,
|
| 413 |
+
"grad_norm": 0.9275403618812561,
|
| 414 |
+
"learning_rate": 8.768774804971705e-06,
|
| 415 |
+
"loss": 0.1813,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.006802721088435,
|
| 420 |
+
"grad_norm": 1.0411152839660645,
|
| 421 |
+
"learning_rate": 8.260550741655337e-06,
|
| 422 |
+
"loss": 0.1558,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0408163265306123,
|
| 427 |
+
"grad_norm": 0.9674392342567444,
|
| 428 |
+
"learning_rate": 7.76184281104011e-06,
|
| 429 |
+
"loss": 0.1048,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.074829931972789,
|
| 434 |
+
"grad_norm": 0.9999818205833435,
|
| 435 |
+
"learning_rate": 7.273355190969783e-06,
|
| 436 |
+
"loss": 0.129,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.108843537414966,
|
| 441 |
+
"grad_norm": 0.922275960445404,
|
| 442 |
+
"learning_rate": 6.795777628163599e-06,
|
| 443 |
+
"loss": 0.1318,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.142857142857143,
|
| 448 |
+
"grad_norm": 0.8856292366981506,
|
| 449 |
+
"learning_rate": 6.329784464290817e-06,
|
| 450 |
+
"loss": 0.1094,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.17687074829932,
|
| 455 |
+
"grad_norm": 1.1011337041854858,
|
| 456 |
+
"learning_rate": 5.8760336837972355e-06,
|
| 457 |
+
"loss": 0.1222,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.2108843537414966,
|
| 462 |
+
"grad_norm": 0.795063316822052,
|
| 463 |
+
"learning_rate": 5.435165984828193e-06,
|
| 464 |
+
"loss": 0.1047,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.2448979591836733,
|
| 469 |
+
"grad_norm": 0.7870824337005615,
|
| 470 |
+
"learning_rate": 5.0078038745599e-06,
|
| 471 |
+
"loss": 0.0998,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.2789115646258504,
|
| 476 |
+
"grad_norm": 1.2127617597579956,
|
| 477 |
+
"learning_rate": 4.594550790216508e-06,
|
| 478 |
+
"loss": 0.1041,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.312925170068027,
|
| 483 |
+
"grad_norm": 0.7656123638153076,
|
| 484 |
+
"learning_rate": 4.195990247014025e-06,
|
| 485 |
+
"loss": 0.1121,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.3469387755102042,
|
| 490 |
+
"grad_norm": 1.0786532163619995,
|
| 491 |
+
"learning_rate": 3.8126850142342114e-06,
|
| 492 |
+
"loss": 0.0998,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.380952380952381,
|
| 497 |
+
"grad_norm": 0.7923595309257507,
|
| 498 |
+
"learning_rate": 3.445176320591806e-06,
|
| 499 |
+
"loss": 0.0973,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.4149659863945576,
|
| 504 |
+
"grad_norm": 0.9183502197265625,
|
| 505 |
+
"learning_rate": 3.0939830900171603e-06,
|
| 506 |
+
"loss": 0.0852,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.4489795918367347,
|
| 511 |
+
"grad_norm": 1.0214210748672485,
|
| 512 |
+
"learning_rate": 2.7596012089333015e-06,
|
| 513 |
+
"loss": 0.0998,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.4829931972789114,
|
| 518 |
+
"grad_norm": 0.8166732788085938,
|
| 519 |
+
"learning_rate": 2.442502826062072e-06,
|
| 520 |
+
"loss": 0.1018,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.5170068027210886,
|
| 525 |
+
"grad_norm": 0.9774287939071655,
|
| 526 |
+
"learning_rate": 2.1431356857480076e-06,
|
| 527 |
+
"loss": 0.0866,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.5510204081632653,
|
| 532 |
+
"grad_norm": 0.7084458470344543,
|
| 533 |
+
"learning_rate": 1.8619224957413106e-06,
|
| 534 |
+
"loss": 0.0936,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.5850340136054424,
|
| 539 |
+
"grad_norm": 0.6899604797363281,
|
| 540 |
+
"learning_rate": 1.5992603303325997e-06,
|
| 541 |
+
"loss": 0.0858,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.619047619047619,
|
| 546 |
+
"grad_norm": 0.8443087339401245,
|
| 547 |
+
"learning_rate": 1.3555200696822235e-06,
|
| 548 |
+
"loss": 0.0872,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.6530612244897958,
|
| 553 |
+
"grad_norm": 0.8087707161903381,
|
| 554 |
+
"learning_rate": 1.1310458761358057e-06,
|
| 555 |
+
"loss": 0.0874,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.687074829931973,
|
| 560 |
+
"grad_norm": 0.8335327506065369,
|
| 561 |
+
"learning_rate": 9.261547082654614e-07,
|
| 562 |
+
"loss": 0.0719,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.7210884353741496,
|
| 567 |
+
"grad_norm": 0.7933460474014282,
|
| 568 |
+
"learning_rate": 7.411358733228679e-07,
|
| 569 |
+
"loss": 0.1016,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.7551020408163263,
|
| 574 |
+
"grad_norm": 0.817876398563385,
|
| 575 |
+
"learning_rate": 5.762506187361206e-07,
|
| 576 |
+
"loss": 0.0846,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.7891156462585034,
|
| 581 |
+
"grad_norm": 0.9033210277557373,
|
| 582 |
+
"learning_rate": 4.317317632271889e-07,
|
| 583 |
+
"loss": 0.0704,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.8231292517006805,
|
| 588 |
+
"grad_norm": 0.7752103805541992,
|
| 589 |
+
"learning_rate": 3.077833680708325e-07,
|
| 590 |
+
"loss": 0.0929,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.857142857142857,
|
| 595 |
+
"grad_norm": 0.9194809198379517,
|
| 596 |
+
"learning_rate": 2.0458044895916516e-07,
|
| 597 |
+
"loss": 0.1021,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.891156462585034,
|
| 602 |
+
"grad_norm": 0.8968177437782288,
|
| 603 |
+
"learning_rate": 1.2226872887870278e-07,
|
| 604 |
+
"loss": 0.0827,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.925170068027211,
|
| 609 |
+
"grad_norm": 0.7262848615646362,
|
| 610 |
+
"learning_rate": 6.096443234885729e-08,
|
| 611 |
+
"loss": 0.072,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.9591836734693877,
|
| 616 |
+
"grad_norm": 0.9196120500564575,
|
| 617 |
+
"learning_rate": 2.0754121312389074e-08,
|
| 618 |
+
"loss": 0.0739,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.9931972789115644,
|
| 623 |
+
"grad_norm": 0.683151364326477,
|
| 624 |
+
"learning_rate": 1.6945729095507733e-09,
|
| 625 |
+
"loss": 0.0855,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.0,
|
| 630 |
+
"step": 441,
|
| 631 |
+
"total_flos": 5.711067727737651e+17,
|
| 632 |
+
"train_loss": 0.4041794179653635,
|
| 633 |
+
"train_runtime": 261.1891,
|
| 634 |
+
"train_samples_per_second": 53.915,
|
| 635 |
+
"train_steps_per_second": 1.688
|
| 636 |
+
}
|
| 637 |
+
],
|
| 638 |
+
"logging_steps": 5,
|
| 639 |
+
"max_steps": 441,
|
| 640 |
+
"num_input_tokens_seen": 0,
|
| 641 |
+
"num_train_epochs": 3,
|
| 642 |
+
"save_steps": 2000,
|
| 643 |
+
"stateful_callbacks": {
|
| 644 |
+
"TrainerControl": {
|
| 645 |
+
"args": {
|
| 646 |
+
"should_epoch_stop": false,
|
| 647 |
+
"should_evaluate": false,
|
| 648 |
+
"should_log": false,
|
| 649 |
+
"should_save": false,
|
| 650 |
+
"should_training_stop": false
|
| 651 |
+
},
|
| 652 |
+
"attributes": {}
|
| 653 |
+
}
|
| 654 |
+
},
|
| 655 |
+
"total_flos": 5.711067727737651e+17,
|
| 656 |
+
"train_batch_size": 2,
|
| 657 |
+
"trial_name": null,
|
| 658 |
+
"trial_params": null
|
| 659 |
+
}
|
117_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74447fbfbde5fa8c76e8f88f19bd50fdbddbb78168b3e891c452932735b0045c
|
| 3 |
+
size 8209
|
117_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|