Training in progress, step 10800, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"q_proj",
|
| 27 |
"k_proj",
|
| 28 |
-
"
|
| 29 |
"o_proj",
|
| 30 |
-
"up_proj",
|
| 31 |
"v_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"down_proj",
|
| 27 |
"q_proj",
|
| 28 |
"k_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
"o_proj",
|
|
|
|
| 31 |
"v_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1556140392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69616034c7478cf2dfccee5c0270ffd5060d30e5019b1fedb3826dd864fdc449
|
| 3 |
size 1556140392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 791682818
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32eee9332b07af811bf55ae350443625f7835082aa14f81cafe85b65410c568c
|
| 3 |
size 791682818
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94ff2db7929a990beccc40066cd3722e70139073f804431d949279fb773ea474
|
| 3 |
size 1064
|
last-checkpoint/tokenizer_config.json
CHANGED
|
@@ -2055,6 +2055,7 @@
|
|
| 2055 |
"clean_up_tokenization_spaces": true,
|
| 2056 |
"eos_token": "<|eot_id|>",
|
| 2057 |
"extra_special_tokens": {},
|
|
|
|
| 2058 |
"model_input_names": [
|
| 2059 |
"input_ids",
|
| 2060 |
"attention_mask"
|
|
@@ -2062,5 +2063,8 @@
|
|
| 2062 |
"model_max_length": 4096,
|
| 2063 |
"pad_token": "<|eot_id|>",
|
| 2064 |
"padding_side": "left",
|
| 2065 |
-
"
|
|
|
|
|
|
|
|
|
|
| 2066 |
}
|
|
|
|
| 2055 |
"clean_up_tokenization_spaces": true,
|
| 2056 |
"eos_token": "<|eot_id|>",
|
| 2057 |
"extra_special_tokens": {},
|
| 2058 |
+
"max_length": 4096,
|
| 2059 |
"model_input_names": [
|
| 2060 |
"input_ids",
|
| 2061 |
"attention_mask"
|
|
|
|
| 2063 |
"model_max_length": 4096,
|
| 2064 |
"pad_token": "<|eot_id|>",
|
| 2065 |
"padding_side": "left",
|
| 2066 |
+
"stride": 0,
|
| 2067 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2068 |
+
"truncation_side": "right",
|
| 2069 |
+
"truncation_strategy": "longest_first"
|
| 2070 |
}
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -28,10 +28,367 @@
|
|
| 28 |
"learning_rate": 1.9999991549580503e-05,
|
| 29 |
"loss": 1.9425,
|
| 30 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
}
|
| 32 |
],
|
| 33 |
"logging_steps": 200,
|
| 34 |
-
"max_steps":
|
| 35 |
"num_input_tokens_seen": 0,
|
| 36 |
"num_train_epochs": 2,
|
| 37 |
"save_steps": 200,
|
|
@@ -47,7 +404,7 @@
|
|
| 47 |
"attributes": {}
|
| 48 |
}
|
| 49 |
},
|
| 50 |
-
"total_flos":
|
| 51 |
"train_batch_size": 1,
|
| 52 |
"trial_name": null,
|
| 53 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.007511209436860982,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 28 |
"learning_rate": 1.9999991549580503e-05,
|
| 29 |
"loss": 1.9425,
|
| 30 |
"step": 600
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0005563858842119246,
|
| 34 |
+
"grad_norm": 1.1521191596984863,
|
| 35 |
+
"learning_rate": 1.999999622846857e-05,
|
| 36 |
+
"loss": 1.8664,
|
| 37 |
+
"step": 800
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0006954823552649058,
|
| 41 |
+
"grad_norm": 1.6058714389801025,
|
| 42 |
+
"learning_rate": 1.999999409214783e-05,
|
| 43 |
+
"loss": 1.7909,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0008345788263178869,
|
| 48 |
+
"grad_norm": 1.3741093873977661,
|
| 49 |
+
"learning_rate": 1.9999991478437182e-05,
|
| 50 |
+
"loss": 1.7653,
|
| 51 |
+
"step": 1200
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0009736752973708681,
|
| 55 |
+
"grad_norm": 1.7162392139434814,
|
| 56 |
+
"learning_rate": 1.9999988387336754e-05,
|
| 57 |
+
"loss": 1.9238,
|
| 58 |
+
"step": 1400
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.001112771768423849,
|
| 62 |
+
"grad_norm": 3.3224897384643555,
|
| 63 |
+
"learning_rate": 1.9999984818846697e-05,
|
| 64 |
+
"loss": 1.8869,
|
| 65 |
+
"step": 1600
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0012518682394768305,
|
| 69 |
+
"grad_norm": 1.6145182847976685,
|
| 70 |
+
"learning_rate": 1.999998077296718e-05,
|
| 71 |
+
"loss": 1.8906,
|
| 72 |
+
"step": 1800
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0013909647105298116,
|
| 76 |
+
"grad_norm": 0.9710016250610352,
|
| 77 |
+
"learning_rate": 1.9999976249698394e-05,
|
| 78 |
+
"loss": 1.8672,
|
| 79 |
+
"step": 2000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0015300611815827927,
|
| 83 |
+
"grad_norm": 1.0537340641021729,
|
| 84 |
+
"learning_rate": 1.9999971249040557e-05,
|
| 85 |
+
"loss": 1.9136,
|
| 86 |
+
"step": 2200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0016691576526357739,
|
| 90 |
+
"grad_norm": 1.443352222442627,
|
| 91 |
+
"learning_rate": 1.9999965770993904e-05,
|
| 92 |
+
"loss": 1.8307,
|
| 93 |
+
"step": 2400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.001808254123688755,
|
| 97 |
+
"grad_norm": 3.0568041801452637,
|
| 98 |
+
"learning_rate": 1.9999959815558703e-05,
|
| 99 |
+
"loss": 1.8695,
|
| 100 |
+
"step": 2600
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0019473505947417361,
|
| 104 |
+
"grad_norm": 0.9355903267860413,
|
| 105 |
+
"learning_rate": 1.9999953382735232e-05,
|
| 106 |
+
"loss": 1.8503,
|
| 107 |
+
"step": 2800
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0020864470657947173,
|
| 111 |
+
"grad_norm": 0.7553691267967224,
|
| 112 |
+
"learning_rate": 1.9999946472523805e-05,
|
| 113 |
+
"loss": 1.9489,
|
| 114 |
+
"step": 3000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.002225543536847698,
|
| 118 |
+
"grad_norm": 0.957789957523346,
|
| 119 |
+
"learning_rate": 1.9999939084924748e-05,
|
| 120 |
+
"loss": 1.854,
|
| 121 |
+
"step": 3200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0023646400079006796,
|
| 125 |
+
"grad_norm": 1.4734654426574707,
|
| 126 |
+
"learning_rate": 1.999993121993841e-05,
|
| 127 |
+
"loss": 1.82,
|
| 128 |
+
"step": 3400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.002503736478953661,
|
| 132 |
+
"grad_norm": 1.5108826160430908,
|
| 133 |
+
"learning_rate": 1.9999922877565166e-05,
|
| 134 |
+
"loss": 1.8743,
|
| 135 |
+
"step": 3600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.002642832950006642,
|
| 139 |
+
"grad_norm": 0.7057523131370544,
|
| 140 |
+
"learning_rate": 1.9999914057805428e-05,
|
| 141 |
+
"loss": 1.9118,
|
| 142 |
+
"step": 3800
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.002781929421059623,
|
| 146 |
+
"grad_norm": 1.4599885940551758,
|
| 147 |
+
"learning_rate": 1.99999047606596e-05,
|
| 148 |
+
"loss": 1.8735,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.002921025892112604,
|
| 153 |
+
"grad_norm": 1.1604583263397217,
|
| 154 |
+
"learning_rate": 1.9999894986128136e-05,
|
| 155 |
+
"loss": 1.8425,
|
| 156 |
+
"step": 4200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0030601223631655855,
|
| 160 |
+
"grad_norm": 0.7119138240814209,
|
| 161 |
+
"learning_rate": 1.99998847342115e-05,
|
| 162 |
+
"loss": 1.8803,
|
| 163 |
+
"step": 4400
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0031992188342185664,
|
| 167 |
+
"grad_norm": 1.1162643432617188,
|
| 168 |
+
"learning_rate": 1.999987400491018e-05,
|
| 169 |
+
"loss": 1.8082,
|
| 170 |
+
"step": 4600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0033383153052715477,
|
| 174 |
+
"grad_norm": 0.9169935584068298,
|
| 175 |
+
"learning_rate": 1.999986279822469e-05,
|
| 176 |
+
"loss": 1.8502,
|
| 177 |
+
"step": 4800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0034774117763245287,
|
| 181 |
+
"grad_norm": 0.8055661916732788,
|
| 182 |
+
"learning_rate": 1.9999851114155563e-05,
|
| 183 |
+
"loss": 1.8665,
|
| 184 |
+
"step": 5000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.00361650824737751,
|
| 188 |
+
"grad_norm": 0.7137724757194519,
|
| 189 |
+
"learning_rate": 1.9999838952703362e-05,
|
| 190 |
+
"loss": 1.8552,
|
| 191 |
+
"step": 5200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.003755604718430491,
|
| 195 |
+
"grad_norm": 0.6924293637275696,
|
| 196 |
+
"learning_rate": 1.9999826313868657e-05,
|
| 197 |
+
"loss": 1.8663,
|
| 198 |
+
"step": 5400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0038947011894834723,
|
| 202 |
+
"grad_norm": 0.9479967951774597,
|
| 203 |
+
"learning_rate": 1.9999813197652065e-05,
|
| 204 |
+
"loss": 1.8452,
|
| 205 |
+
"step": 5600
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.004033797660536453,
|
| 209 |
+
"grad_norm": 0.8143343329429626,
|
| 210 |
+
"learning_rate": 1.99997996040542e-05,
|
| 211 |
+
"loss": 1.8846,
|
| 212 |
+
"step": 5800
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.004172894131589435,
|
| 216 |
+
"grad_norm": 1.111542820930481,
|
| 217 |
+
"learning_rate": 1.999978553307572e-05,
|
| 218 |
+
"loss": 1.9686,
|
| 219 |
+
"step": 6000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.004311990602642416,
|
| 223 |
+
"grad_norm": 0.7616419792175293,
|
| 224 |
+
"learning_rate": 1.999977098471729e-05,
|
| 225 |
+
"loss": 1.8488,
|
| 226 |
+
"step": 6200
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.004451087073695396,
|
| 230 |
+
"grad_norm": 1.4848086833953857,
|
| 231 |
+
"learning_rate": 1.999975595897961e-05,
|
| 232 |
+
"loss": 1.8701,
|
| 233 |
+
"step": 6400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.004590183544748378,
|
| 237 |
+
"grad_norm": 1.7007120847702026,
|
| 238 |
+
"learning_rate": 1.9999740455863392e-05,
|
| 239 |
+
"loss": 1.8166,
|
| 240 |
+
"step": 6600
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.004729280015801359,
|
| 244 |
+
"grad_norm": 0.7468813061714172,
|
| 245 |
+
"learning_rate": 1.999972447536938e-05,
|
| 246 |
+
"loss": 1.8487,
|
| 247 |
+
"step": 6800
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.0048683764868543405,
|
| 251 |
+
"grad_norm": 1.2272229194641113,
|
| 252 |
+
"learning_rate": 1.9999708017498335e-05,
|
| 253 |
+
"loss": 1.8977,
|
| 254 |
+
"step": 7000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.005007472957907322,
|
| 258 |
+
"grad_norm": 0.889249861240387,
|
| 259 |
+
"learning_rate": 1.9999691082251046e-05,
|
| 260 |
+
"loss": 1.796,
|
| 261 |
+
"step": 7200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.005146569428960302,
|
| 265 |
+
"grad_norm": 0.8674280643463135,
|
| 266 |
+
"learning_rate": 1.9999673669628317e-05,
|
| 267 |
+
"loss": 1.8211,
|
| 268 |
+
"step": 7400
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.005285665900013284,
|
| 272 |
+
"grad_norm": 0.9621294736862183,
|
| 273 |
+
"learning_rate": 1.9999655779630983e-05,
|
| 274 |
+
"loss": 1.8682,
|
| 275 |
+
"step": 7600
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.005424762371066265,
|
| 279 |
+
"grad_norm": 0.6938799619674683,
|
| 280 |
+
"learning_rate": 1.9999637412259892e-05,
|
| 281 |
+
"loss": 1.826,
|
| 282 |
+
"step": 7800
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.005563858842119246,
|
| 286 |
+
"grad_norm": 0.9145010709762573,
|
| 287 |
+
"learning_rate": 1.9999618567515927e-05,
|
| 288 |
+
"loss": 1.8725,
|
| 289 |
+
"step": 8000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.005702955313172227,
|
| 293 |
+
"grad_norm": 0.8468737006187439,
|
| 294 |
+
"learning_rate": 1.999959924539999e-05,
|
| 295 |
+
"loss": 1.7994,
|
| 296 |
+
"step": 8200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.005842051784225208,
|
| 300 |
+
"grad_norm": 2.022569179534912,
|
| 301 |
+
"learning_rate": 1.9999579445912994e-05,
|
| 302 |
+
"loss": 1.8348,
|
| 303 |
+
"step": 8400
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.00598114825527819,
|
| 307 |
+
"grad_norm": 0.7492377161979675,
|
| 308 |
+
"learning_rate": 1.9999559169055893e-05,
|
| 309 |
+
"loss": 1.8122,
|
| 310 |
+
"step": 8600
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.006120244726331171,
|
| 314 |
+
"grad_norm": 1.3001569509506226,
|
| 315 |
+
"learning_rate": 1.999953841482965e-05,
|
| 316 |
+
"loss": 1.7776,
|
| 317 |
+
"step": 8800
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.006259341197384151,
|
| 321 |
+
"grad_norm": 1.238887071609497,
|
| 322 |
+
"learning_rate": 1.9999517183235256e-05,
|
| 323 |
+
"loss": 1.7954,
|
| 324 |
+
"step": 9000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.006398437668437133,
|
| 328 |
+
"grad_norm": 0.9216433763504028,
|
| 329 |
+
"learning_rate": 1.9999495474273724e-05,
|
| 330 |
+
"loss": 1.8619,
|
| 331 |
+
"step": 9200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.006537534139490114,
|
| 335 |
+
"grad_norm": 1.2052515745162964,
|
| 336 |
+
"learning_rate": 1.9999473287946092e-05,
|
| 337 |
+
"loss": 1.8636,
|
| 338 |
+
"step": 9400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.0066766306105430955,
|
| 342 |
+
"grad_norm": 1.1095556020736694,
|
| 343 |
+
"learning_rate": 1.9999450624253423e-05,
|
| 344 |
+
"loss": 1.8283,
|
| 345 |
+
"step": 9600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.006815727081596076,
|
| 349 |
+
"grad_norm": 0.681342363357544,
|
| 350 |
+
"learning_rate": 1.9999427483196793e-05,
|
| 351 |
+
"loss": 1.868,
|
| 352 |
+
"step": 9800
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.006954823552649057,
|
| 356 |
+
"grad_norm": 1.1534216403961182,
|
| 357 |
+
"learning_rate": 1.999940386477731e-05,
|
| 358 |
+
"loss": 1.8575,
|
| 359 |
+
"step": 10000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.007093920023702039,
|
| 363 |
+
"grad_norm": 0.7867778539657593,
|
| 364 |
+
"learning_rate": 1.99993797689961e-05,
|
| 365 |
+
"loss": 1.8735,
|
| 366 |
+
"step": 10200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.00723301649475502,
|
| 370 |
+
"grad_norm": 0.9070300459861755,
|
| 371 |
+
"learning_rate": 1.999935519585431e-05,
|
| 372 |
+
"loss": 1.817,
|
| 373 |
+
"step": 10400
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.007372112965808001,
|
| 377 |
+
"grad_norm": 0.830132782459259,
|
| 378 |
+
"learning_rate": 1.9999330145353123e-05,
|
| 379 |
+
"loss": 1.8442,
|
| 380 |
+
"step": 10600
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.007511209436860982,
|
| 384 |
+
"grad_norm": 0.6420764923095703,
|
| 385 |
+
"learning_rate": 1.9999304617493725e-05,
|
| 386 |
+
"loss": 1.8847,
|
| 387 |
+
"step": 10800
|
| 388 |
}
|
| 389 |
],
|
| 390 |
"logging_steps": 200,
|
| 391 |
+
"max_steps": 2875702,
|
| 392 |
"num_input_tokens_seen": 0,
|
| 393 |
"num_train_epochs": 2,
|
| 394 |
"save_steps": 200,
|
|
|
|
| 404 |
"attributes": {}
|
| 405 |
}
|
| 406 |
},
|
| 407 |
+
"total_flos": 6.271390014938726e+16,
|
| 408 |
"train_batch_size": 1,
|
| 409 |
"trial_name": null,
|
| 410 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9904b88a607b9ec7e7c8f68db2631b21b2e901d7835fe093b513a58fc6cba17
|
| 3 |
size 6776
|