Training in progress, step 4000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779a82879b0841465ca1b858d82cac1e88868b011b357cbb5ae641bc4467a2fd
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd40a78565e4f7ddfb41d95ac5573fea5bc25afd2bad35a7bf584b0f9012d4d
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e8e748d681e6f71f9b57ae68d6afe316f465cbd0f520ceb97f2e75d98b46b73
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b3af4aaa142e4a55ebe50a8d2db120dc2b7b23b5e6bb84de2f69f7d1627803e
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,79 +2,331 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 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.
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 0.00066,
|
| 16 |
-
"loss": 7.
|
| 17 |
"step": 100
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"step": 100
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch": 0.
|
| 29 |
-
"grad_norm": 0.
|
| 30 |
-
"learning_rate": 0.
|
| 31 |
-
"loss": 5.
|
| 32 |
-
"step":
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"step": 200
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"epoch": 0.
|
| 44 |
-
"grad_norm": 0.
|
| 45 |
-
"learning_rate": 0.
|
| 46 |
-
"loss":
|
| 47 |
-
"step":
|
| 48 |
},
|
| 49 |
{
|
| 50 |
-
"epoch": 0.
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"step": 300
|
| 56 |
},
|
| 57 |
{
|
| 58 |
-
"epoch": 0.
|
| 59 |
-
"grad_norm": 0.
|
| 60 |
-
"learning_rate": 0.
|
| 61 |
-
"loss": 4.
|
| 62 |
-
"step":
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|
| 72 |
],
|
| 73 |
"logging_steps": 100,
|
| 74 |
-
"max_steps":
|
| 75 |
"num_input_tokens_seen": 0,
|
| 76 |
"num_train_epochs": 9223372036854775807,
|
| 77 |
-
"save_steps":
|
| 78 |
"stateful_callbacks": {
|
| 79 |
"TrainerControl": {
|
| 80 |
"args": {
|
|
@@ -87,7 +339,7 @@
|
|
| 87 |
"attributes": {}
|
| 88 |
}
|
| 89 |
},
|
| 90 |
-
"total_flos":
|
| 91 |
"train_batch_size": 22,
|
| 92 |
"trial_name": null,
|
| 93 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03636363636363636,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.0009090909090909091,
|
| 14 |
+
"grad_norm": 0.5637483596801758,
|
| 15 |
"learning_rate": 0.00066,
|
| 16 |
+
"loss": 7.38281005859375,
|
| 17 |
"step": 100
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.0018181818181818182,
|
| 21 |
+
"grad_norm": 0.6073591709136963,
|
| 22 |
+
"learning_rate": 0.000999999509056267,
|
| 23 |
+
"loss": 5.783165283203125,
|
| 24 |
+
"step": 200
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.0027272727272727275,
|
| 28 |
+
"grad_norm": 0.480266273021698,
|
| 29 |
+
"learning_rate": 0.0009999954604635122,
|
| 30 |
+
"loss": 5.232196044921875,
|
| 31 |
+
"step": 300
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.0036363636363636364,
|
| 35 |
+
"grad_norm": 0.45949065685272217,
|
| 36 |
+
"learning_rate": 0.0009999873224161853,
|
| 37 |
+
"loss": 4.946490478515625,
|
| 38 |
+
"step": 400
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.004545454545454545,
|
| 42 |
+
"grad_norm": 0.41542109847068787,
|
| 43 |
+
"learning_rate": 0.000999975094980847,
|
| 44 |
+
"loss": 4.719376831054688,
|
| 45 |
+
"step": 500
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.005454545454545455,
|
| 49 |
+
"grad_norm": 0.40697741508483887,
|
| 50 |
+
"learning_rate": 0.0009999587782575051,
|
| 51 |
+
"loss": 4.591694030761719,
|
| 52 |
+
"step": 600
|
|
|
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.006363636363636364,
|
| 56 |
+
"grad_norm": 0.3962944447994232,
|
| 57 |
+
"learning_rate": 0.0009999383723796143,
|
| 58 |
+
"loss": 4.466532592773437,
|
| 59 |
+
"step": 700
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.007272727272727273,
|
| 63 |
+
"grad_norm": 0.6857792139053345,
|
| 64 |
+
"learning_rate": 0.0009999138775140734,
|
| 65 |
+
"loss": 4.349520874023438,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.008181818181818182,
|
| 70 |
+
"grad_norm": 0.4181463420391083,
|
| 71 |
+
"learning_rate": 0.000999885293861226,
|
| 72 |
+
"loss": 4.234326782226563,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.00909090909090909,
|
| 77 |
+
"grad_norm": 0.3620698153972626,
|
| 78 |
+
"learning_rate": 0.0009998526216548572,
|
| 79 |
+
"loss": 4.120015869140625,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.00909090909090909,
|
| 84 |
+
"eval_loss": 4.375123977661133,
|
| 85 |
+
"eval_runtime": 6.9666,
|
| 86 |
+
"eval_samples_per_second": 82.681,
|
| 87 |
+
"eval_steps_per_second": 20.67,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.01,
|
| 92 |
+
"grad_norm": 0.3509594798088074,
|
| 93 |
+
"learning_rate": 0.0009998158611621922,
|
| 94 |
+
"loss": 3.993647155761719,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.01090909090909091,
|
| 99 |
+
"grad_norm": 0.3581515848636627,
|
| 100 |
+
"learning_rate": 0.0009997750126838946,
|
| 101 |
+
"loss": 3.9498220825195314,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.011818181818181818,
|
| 106 |
+
"grad_norm": 0.36733096837997437,
|
| 107 |
+
"learning_rate": 0.0009997300765540635,
|
| 108 |
+
"loss": 3.831287841796875,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.012727272727272728,
|
| 113 |
+
"grad_norm": 0.29147249460220337,
|
| 114 |
+
"learning_rate": 0.0009996810531402306,
|
| 115 |
+
"loss": 3.7590908813476562,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.013636363636363636,
|
| 120 |
+
"grad_norm": 0.29391637444496155,
|
| 121 |
+
"learning_rate": 0.0009996279428433578,
|
| 122 |
+
"loss": 3.722886047363281,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.014545454545454545,
|
| 127 |
+
"grad_norm": 0.3317511975765228,
|
| 128 |
+
"learning_rate": 0.000999570746097833,
|
| 129 |
+
"loss": 3.7012667846679688,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.015454545454545455,
|
| 134 |
+
"grad_norm": 0.32525742053985596,
|
| 135 |
+
"learning_rate": 0.0009995094633714677,
|
| 136 |
+
"loss": 3.6526870727539062,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.016363636363636365,
|
| 141 |
+
"grad_norm": 0.3586934208869934,
|
| 142 |
+
"learning_rate": 0.0009994440951654924,
|
| 143 |
+
"loss": 3.6262481689453123,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.017272727272727273,
|
| 148 |
+
"grad_norm": 0.30995482206344604,
|
| 149 |
+
"learning_rate": 0.0009993746420145523,
|
| 150 |
+
"loss": 3.594487609863281,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.01818181818181818,
|
| 155 |
+
"grad_norm": 0.3067973852157593,
|
| 156 |
+
"learning_rate": 0.0009993011044867038,
|
| 157 |
+
"loss": 3.5707028198242186,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.01818181818181818,
|
| 162 |
+
"eval_loss": 3.896928548812866,
|
| 163 |
+
"eval_runtime": 6.7872,
|
| 164 |
+
"eval_samples_per_second": 84.865,
|
| 165 |
+
"eval_steps_per_second": 21.216,
|
| 166 |
+
"step": 2000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.019090909090909092,
|
| 170 |
+
"grad_norm": 0.2716964781284332,
|
| 171 |
+
"learning_rate": 0.000999223483183409,
|
| 172 |
+
"loss": 3.5685223388671874,
|
| 173 |
+
"step": 2100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.02,
|
| 177 |
+
"grad_norm": 0.2595560550689697,
|
| 178 |
+
"learning_rate": 0.000999141778739531,
|
| 179 |
+
"loss": 3.533115234375,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.02090909090909091,
|
| 184 |
+
"grad_norm": 0.2871851325035095,
|
| 185 |
+
"learning_rate": 0.0009990559918233294,
|
| 186 |
+
"loss": 3.51209716796875,
|
| 187 |
+
"step": 2300
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.02181818181818182,
|
| 191 |
+
"grad_norm": 0.2916632890701294,
|
| 192 |
+
"learning_rate": 0.0009989661231364542,
|
| 193 |
+
"loss": 3.4977175903320314,
|
| 194 |
+
"step": 2400
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.022727272727272728,
|
| 198 |
+
"grad_norm": 0.2674938440322876,
|
| 199 |
+
"learning_rate": 0.0009988721734139395,
|
| 200 |
+
"loss": 3.4819268798828125,
|
| 201 |
+
"step": 2500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.023636363636363636,
|
| 205 |
+
"grad_norm": 0.28354012966156006,
|
| 206 |
+
"learning_rate": 0.0009987741434241983,
|
| 207 |
+
"loss": 3.4985772705078126,
|
| 208 |
+
"step": 2600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.024545454545454544,
|
| 212 |
+
"grad_norm": 0.250453919172287,
|
| 213 |
+
"learning_rate": 0.000998672033969017,
|
| 214 |
+
"loss": 3.4824765014648436,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.025454545454545455,
|
| 219 |
+
"grad_norm": 0.25479111075401306,
|
| 220 |
+
"learning_rate": 0.0009985658458835465,
|
| 221 |
+
"loss": 3.43513916015625,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.026363636363636363,
|
| 226 |
+
"grad_norm": 0.5312749743461609,
|
| 227 |
+
"learning_rate": 0.0009984555800362977,
|
| 228 |
+
"loss": 3.4338519287109377,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.02727272727272727,
|
| 233 |
+
"grad_norm": 0.24919964373111725,
|
| 234 |
+
"learning_rate": 0.0009983412373291332,
|
| 235 |
+
"loss": 3.394432373046875,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.02727272727272727,
|
| 240 |
+
"eval_loss": 3.7320191860198975,
|
| 241 |
+
"eval_runtime": 6.8112,
|
| 242 |
+
"eval_samples_per_second": 84.566,
|
| 243 |
+
"eval_steps_per_second": 21.142,
|
| 244 |
+
"step": 3000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.028181818181818183,
|
| 248 |
+
"grad_norm": 0.2345028668642044,
|
| 249 |
+
"learning_rate": 0.0009982228186972597,
|
| 250 |
+
"loss": 3.3772811889648438,
|
| 251 |
+
"step": 3100
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.02909090909090909,
|
| 255 |
+
"grad_norm": 0.2587430775165558,
|
| 256 |
+
"learning_rate": 0.0009981003251092215,
|
| 257 |
+
"loss": 3.368675537109375,
|
| 258 |
+
"step": 3200
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.03,
|
| 262 |
+
"grad_norm": 0.25332900881767273,
|
| 263 |
+
"learning_rate": 0.0009979737575668917,
|
| 264 |
+
"loss": 3.3781060791015625,
|
| 265 |
+
"step": 3300
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.03090909090909091,
|
| 269 |
+
"grad_norm": 0.2273174375295639,
|
| 270 |
+
"learning_rate": 0.000997843117105464,
|
| 271 |
+
"loss": 3.328343505859375,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.031818181818181815,
|
| 276 |
+
"grad_norm": 0.2621140778064728,
|
| 277 |
+
"learning_rate": 0.0009977084047934448,
|
| 278 |
+
"loss": 3.3511767578125,
|
| 279 |
+
"step": 3500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.03272727272727273,
|
| 283 |
+
"grad_norm": 0.22301150858402252,
|
| 284 |
+
"learning_rate": 0.0009975696217326435,
|
| 285 |
+
"loss": 3.3483154296875,
|
| 286 |
+
"step": 3600
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.03363636363636364,
|
| 290 |
+
"grad_norm": 0.22785483300685883,
|
| 291 |
+
"learning_rate": 0.0009974267690581644,
|
| 292 |
+
"loss": 3.351199951171875,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.034545454545454546,
|
| 297 |
+
"grad_norm": 0.24507705867290497,
|
| 298 |
+
"learning_rate": 0.0009972798479383977,
|
| 299 |
+
"loss": 3.311331787109375,
|
| 300 |
+
"step": 3800
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.035454545454545454,
|
| 304 |
+
"grad_norm": 0.22445634007453918,
|
| 305 |
+
"learning_rate": 0.0009971288595750083,
|
| 306 |
+
"loss": 3.2849237060546876,
|
| 307 |
+
"step": 3900
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.03636363636363636,
|
| 311 |
+
"grad_norm": 0.2134762406349182,
|
| 312 |
+
"learning_rate": 0.0009969738052029277,
|
| 313 |
+
"loss": 3.2534124755859377,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.03636363636363636,
|
| 318 |
+
"eval_loss": 3.6267645359039307,
|
| 319 |
+
"eval_runtime": 6.8001,
|
| 320 |
+
"eval_samples_per_second": 84.704,
|
| 321 |
+
"eval_steps_per_second": 21.176,
|
| 322 |
+
"step": 4000
|
| 323 |
}
|
| 324 |
],
|
| 325 |
"logging_steps": 100,
|
| 326 |
+
"max_steps": 110000,
|
| 327 |
"num_input_tokens_seen": 0,
|
| 328 |
"num_train_epochs": 9223372036854775807,
|
| 329 |
+
"save_steps": 4000,
|
| 330 |
"stateful_callbacks": {
|
| 331 |
"TrainerControl": {
|
| 332 |
"args": {
|
|
|
|
| 339 |
"attributes": {}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
+
"total_flos": 9.9658323984384e+16,
|
| 343 |
"train_batch_size": 22,
|
| 344 |
"trial_name": null,
|
| 345 |
"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 5201
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:567e8406e27dd015c52febc5cd0c60d00147e3fcfbac62fe7f312af41586ea47
|
| 3 |
size 5201
|