FastPlus Backup checkpoint-400 at global step 400
Browse files- checkpoint-400/config.json +19 -0
- checkpoint-400/generation_config.json +6 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/trainer_state.json +354 -0
- checkpoint-400/training_args.bin +3 -0
checkpoint-400/config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastPlusForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"intermediate_size": 2304,
|
| 9 |
+
"kd_alpha": 0.4,
|
| 10 |
+
"kd_temperature": 2.5,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "fastplus",
|
| 13 |
+
"num_attention_heads": 12,
|
| 14 |
+
"num_hidden_layers": 12,
|
| 15 |
+
"tie_word_embeddings": true,
|
| 16 |
+
"transformers_version": "5.12.0",
|
| 17 |
+
"use_cache": false,
|
| 18 |
+
"vocab_size": 31968
|
| 19 |
+
}
|
checkpoint-400/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.12.0"
|
| 6 |
+
}
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c089042d567e6b1ffa88f0535997d035a70a4cfe827887861ecdfb609a5130
|
| 3 |
+
size 395782848
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1b1220459cd2cd09f96f6676e13dda56c1305012bcc9bd9dc87d45f29b43ce9
|
| 3 |
+
size 444577931
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b6e628a28bafb3c6f308c8ad5910e07e5c48e59cb952f0bc5a244ce6b04a2e
|
| 3 |
+
size 1383
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15531c53a8cd62608a63b706caa34f82c21c069ddfbca29b8701f4681241490b
|
| 3 |
+
size 6009
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,354 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.013333333333333334,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0003333333333333333,
|
| 14 |
+
"grad_norm": 246.00827026367188,
|
| 15 |
+
"learning_rate": 4.76e-06,
|
| 16 |
+
"loss": 166.319970703125,
|
| 17 |
+
"original_ce_loss": 10.3945,
|
| 18 |
+
"step": 10
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0006666666666666666,
|
| 22 |
+
"grad_norm": 244.34457397460938,
|
| 23 |
+
"learning_rate": 1.1560000000000001e-05,
|
| 24 |
+
"loss": 166.11895751953125,
|
| 25 |
+
"original_ce_loss": 10.3819,
|
| 26 |
+
"step": 20
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.001,
|
| 30 |
+
"grad_norm": 243.96890258789062,
|
| 31 |
+
"learning_rate": 1.836e-05,
|
| 32 |
+
"loss": 165.62098388671876,
|
| 33 |
+
"original_ce_loss": 10.3508,
|
| 34 |
+
"step": 30
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.0013333333333333333,
|
| 38 |
+
"grad_norm": 268.2583312988281,
|
| 39 |
+
"learning_rate": 2.516e-05,
|
| 40 |
+
"loss": 164.65194091796874,
|
| 41 |
+
"original_ce_loss": 10.2902,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0016666666666666668,
|
| 46 |
+
"grad_norm": 315.6184997558594,
|
| 47 |
+
"learning_rate": 3.1960000000000006e-05,
|
| 48 |
+
"loss": 162.7759521484375,
|
| 49 |
+
"original_ce_loss": 10.173,
|
| 50 |
+
"step": 50
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.002,
|
| 54 |
+
"grad_norm": 378.4802551269531,
|
| 55 |
+
"learning_rate": 3.876e-05,
|
| 56 |
+
"loss": 158.40428466796874,
|
| 57 |
+
"original_ce_loss": 9.8997,
|
| 58 |
+
"step": 60
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0023333333333333335,
|
| 62 |
+
"grad_norm": 178.61724853515625,
|
| 63 |
+
"learning_rate": 4.4880000000000004e-05,
|
| 64 |
+
"loss": 148.0895263671875,
|
| 65 |
+
"original_ce_loss": 9.2551,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0026666666666666666,
|
| 70 |
+
"grad_norm": 58.28500747680664,
|
| 71 |
+
"learning_rate": 5.168e-05,
|
| 72 |
+
"loss": 139.22628173828124,
|
| 73 |
+
"original_ce_loss": 8.7011,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.003,
|
| 78 |
+
"grad_norm": NaN,
|
| 79 |
+
"learning_rate": 5.780000000000001e-05,
|
| 80 |
+
"loss": 133.89996337890625,
|
| 81 |
+
"original_ce_loss": 8.3682,
|
| 82 |
+
"step": 90
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0033333333333333335,
|
| 86 |
+
"grad_norm": NaN,
|
| 87 |
+
"learning_rate": 5.848e-05,
|
| 88 |
+
"loss": 131.97056884765624,
|
| 89 |
+
"original_ce_loss": 8.2476,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.0036666666666666666,
|
| 94 |
+
"grad_norm": 45.780582427978516,
|
| 95 |
+
"learning_rate": 6.392000000000001e-05,
|
| 96 |
+
"loss": 129.279736328125,
|
| 97 |
+
"original_ce_loss": 8.0794,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.004,
|
| 102 |
+
"grad_norm": 38.22166442871094,
|
| 103 |
+
"learning_rate": 7.072e-05,
|
| 104 |
+
"loss": 124.1231689453125,
|
| 105 |
+
"original_ce_loss": 7.7572,
|
| 106 |
+
"step": 120
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.004333333333333333,
|
| 110 |
+
"grad_norm": 34.60215377807617,
|
| 111 |
+
"learning_rate": 7.752e-05,
|
| 112 |
+
"loss": 119.131298828125,
|
| 113 |
+
"original_ce_loss": 7.4452,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004666666666666667,
|
| 118 |
+
"grad_norm": 27.215518951416016,
|
| 119 |
+
"learning_rate": 8.432e-05,
|
| 120 |
+
"loss": 114.3770263671875,
|
| 121 |
+
"original_ce_loss": 7.148,
|
| 122 |
+
"step": 140
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.005,
|
| 126 |
+
"grad_norm": 27.311050415039062,
|
| 127 |
+
"learning_rate": 9.112000000000001e-05,
|
| 128 |
+
"loss": 110.84078369140624,
|
| 129 |
+
"original_ce_loss": 6.927,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.005333333333333333,
|
| 134 |
+
"grad_norm": 29.360546112060547,
|
| 135 |
+
"learning_rate": 9.792e-05,
|
| 136 |
+
"loss": 108.61451416015625,
|
| 137 |
+
"original_ce_loss": 6.7879,
|
| 138 |
+
"step": 160
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.005666666666666667,
|
| 142 |
+
"grad_norm": 30.510602951049805,
|
| 143 |
+
"learning_rate": 0.00010472,
|
| 144 |
+
"loss": 108.4002685546875,
|
| 145 |
+
"original_ce_loss": 6.7745,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.006,
|
| 150 |
+
"grad_norm": 34.6984977722168,
|
| 151 |
+
"learning_rate": 0.00011152000000000002,
|
| 152 |
+
"loss": 108.417431640625,
|
| 153 |
+
"original_ce_loss": 6.7756,
|
| 154 |
+
"step": 180
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.006333333333333333,
|
| 158 |
+
"grad_norm": 26.99405288696289,
|
| 159 |
+
"learning_rate": 0.00011832,
|
| 160 |
+
"loss": 108.10020751953125,
|
| 161 |
+
"original_ce_loss": 6.7557,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.006666666666666667,
|
| 166 |
+
"grad_norm": 53.1820068359375,
|
| 167 |
+
"learning_rate": 0.00012512,
|
| 168 |
+
"loss": 106.81435546875,
|
| 169 |
+
"original_ce_loss": 6.6754,
|
| 170 |
+
"step": 200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.007,
|
| 174 |
+
"grad_norm": 30.569377899169922,
|
| 175 |
+
"learning_rate": 0.00013192000000000002,
|
| 176 |
+
"loss": 107.0900146484375,
|
| 177 |
+
"original_ce_loss": 6.6926,
|
| 178 |
+
"step": 210
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.007333333333333333,
|
| 182 |
+
"grad_norm": 32.936912536621094,
|
| 183 |
+
"learning_rate": 0.00013872,
|
| 184 |
+
"loss": 106.95457763671875,
|
| 185 |
+
"original_ce_loss": 6.6841,
|
| 186 |
+
"step": 220
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.007666666666666666,
|
| 190 |
+
"grad_norm": 29.5030517578125,
|
| 191 |
+
"learning_rate": 0.00014552,
|
| 192 |
+
"loss": 107.0662841796875,
|
| 193 |
+
"original_ce_loss": 6.6911,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.008,
|
| 198 |
+
"grad_norm": 62.31581115722656,
|
| 199 |
+
"learning_rate": 0.00015232,
|
| 200 |
+
"loss": 107.4040283203125,
|
| 201 |
+
"original_ce_loss": 6.7122,
|
| 202 |
+
"step": 240
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.008333333333333333,
|
| 206 |
+
"grad_norm": 21.973918914794922,
|
| 207 |
+
"learning_rate": 0.00015912,
|
| 208 |
+
"loss": 106.131591796875,
|
| 209 |
+
"original_ce_loss": 6.6327,
|
| 210 |
+
"step": 250
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.008666666666666666,
|
| 214 |
+
"grad_norm": 15.56334400177002,
|
| 215 |
+
"learning_rate": 0.00016592,
|
| 216 |
+
"loss": 105.91175537109375,
|
| 217 |
+
"original_ce_loss": 6.619,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.009,
|
| 222 |
+
"grad_norm": 30.805395126342773,
|
| 223 |
+
"learning_rate": 0.00017272,
|
| 224 |
+
"loss": 105.45435791015625,
|
| 225 |
+
"original_ce_loss": 6.5904,
|
| 226 |
+
"step": 270
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.009333333333333334,
|
| 230 |
+
"grad_norm": 26.830305099487305,
|
| 231 |
+
"learning_rate": 0.00017952000000000002,
|
| 232 |
+
"loss": 105.6036376953125,
|
| 233 |
+
"original_ce_loss": 6.5997,
|
| 234 |
+
"step": 280
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.009666666666666667,
|
| 238 |
+
"grad_norm": 41.400184631347656,
|
| 239 |
+
"learning_rate": 0.00018632000000000002,
|
| 240 |
+
"loss": 105.23748779296875,
|
| 241 |
+
"original_ce_loss": 6.5768,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.01,
|
| 246 |
+
"grad_norm": 20.883922576904297,
|
| 247 |
+
"learning_rate": 0.00019312,
|
| 248 |
+
"loss": 105.05906982421875,
|
| 249 |
+
"original_ce_loss": 6.5657,
|
| 250 |
+
"step": 300
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.010333333333333333,
|
| 254 |
+
"grad_norm": 43.33014678955078,
|
| 255 |
+
"learning_rate": 0.00019992,
|
| 256 |
+
"loss": 105.232763671875,
|
| 257 |
+
"original_ce_loss": 6.5765,
|
| 258 |
+
"step": 310
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.010666666666666666,
|
| 262 |
+
"grad_norm": 27.369783401489258,
|
| 263 |
+
"learning_rate": 0.00020672,
|
| 264 |
+
"loss": 105.67841796875,
|
| 265 |
+
"original_ce_loss": 6.6044,
|
| 266 |
+
"step": 320
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.011,
|
| 270 |
+
"grad_norm": 31.567529678344727,
|
| 271 |
+
"learning_rate": 0.00021352000000000003,
|
| 272 |
+
"loss": 105.58756103515626,
|
| 273 |
+
"original_ce_loss": 6.5987,
|
| 274 |
+
"step": 330
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.011333333333333334,
|
| 278 |
+
"grad_norm": 60.09785461425781,
|
| 279 |
+
"learning_rate": 0.00022032000000000003,
|
| 280 |
+
"loss": 105.2715087890625,
|
| 281 |
+
"original_ce_loss": 6.5789,
|
| 282 |
+
"step": 340
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.011666666666666667,
|
| 286 |
+
"grad_norm": 19.22910499572754,
|
| 287 |
+
"learning_rate": 0.00022712000000000003,
|
| 288 |
+
"loss": 105.53642578125,
|
| 289 |
+
"original_ce_loss": 6.5955,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.012,
|
| 294 |
+
"grad_norm": 27.537559509277344,
|
| 295 |
+
"learning_rate": 0.00023392,
|
| 296 |
+
"loss": 105.73619384765625,
|
| 297 |
+
"original_ce_loss": 6.608,
|
| 298 |
+
"step": 360
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.012333333333333333,
|
| 302 |
+
"grad_norm": 13.742098808288574,
|
| 303 |
+
"learning_rate": 0.00024072,
|
| 304 |
+
"loss": 105.0564453125,
|
| 305 |
+
"original_ce_loss": 6.5655,
|
| 306 |
+
"step": 370
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.012666666666666666,
|
| 310 |
+
"grad_norm": 666.3156127929688,
|
| 311 |
+
"learning_rate": 0.00024752,
|
| 312 |
+
"loss": 106.70162353515624,
|
| 313 |
+
"original_ce_loss": 6.6683,
|
| 314 |
+
"step": 380
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.013,
|
| 318 |
+
"grad_norm": 420.6439514160156,
|
| 319 |
+
"learning_rate": 0.00025432,
|
| 320 |
+
"loss": 105.82598876953125,
|
| 321 |
+
"original_ce_loss": 6.6136,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.013333333333333334,
|
| 326 |
+
"grad_norm": 2865.46533203125,
|
| 327 |
+
"learning_rate": 0.00026112000000000005,
|
| 328 |
+
"loss": 108.68109130859375,
|
| 329 |
+
"original_ce_loss": 6.792,
|
| 330 |
+
"step": 400
|
| 331 |
+
}
|
| 332 |
+
],
|
| 333 |
+
"logging_steps": 10,
|
| 334 |
+
"max_steps": 30000,
|
| 335 |
+
"num_input_tokens_seen": 0,
|
| 336 |
+
"num_train_epochs": 9223372036854775807,
|
| 337 |
+
"save_steps": 200,
|
| 338 |
+
"stateful_callbacks": {
|
| 339 |
+
"TrainerControl": {
|
| 340 |
+
"args": {
|
| 341 |
+
"should_epoch_stop": false,
|
| 342 |
+
"should_evaluate": false,
|
| 343 |
+
"should_log": false,
|
| 344 |
+
"should_save": true,
|
| 345 |
+
"should_training_stop": false
|
| 346 |
+
},
|
| 347 |
+
"attributes": {}
|
| 348 |
+
}
|
| 349 |
+
},
|
| 350 |
+
"total_flos": 2.94745836355584e+16,
|
| 351 |
+
"train_batch_size": 16,
|
| 352 |
+
"trial_name": null,
|
| 353 |
+
"trial_params": null
|
| 354 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25417f401430668fae7517ca595e0978a628165e7693ec7a7a5f83234373edb0
|
| 3 |
+
size 5137
|