Upload 5 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +144 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab790d3e5298ae9db09e71b1872e1b3b9875e3c39a778816613a20f3276a1903
|
| 3 |
+
size 5885590
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db9feae642274caf5f2085e4241f4b451df45c81a3c5c9b1aa3c8dd8e5ca155
|
| 3 |
+
size 14503
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c72eb02261b9afad4d2943f2907af0c5e11074ebf8fdf590c584dbcaf959d1
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2de9f97e4e42495ec8d46f258233cea6f7a38b9c611fdd15b8cc05ae6c8e1dc7
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.2248995983935744,
|
| 5 |
+
"global_step": 69,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 0.0008709677419354839,
|
| 13 |
+
"loss": 2.7331,
|
| 14 |
+
"step": 4
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.26,
|
| 18 |
+
"learning_rate": 0.0007419354838709678,
|
| 19 |
+
"loss": 2.6157,
|
| 20 |
+
"step": 8
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.39,
|
| 24 |
+
"learning_rate": 0.0006129032258064516,
|
| 25 |
+
"loss": 2.566,
|
| 26 |
+
"step": 12
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.51,
|
| 30 |
+
"learning_rate": 0.0004838709677419355,
|
| 31 |
+
"loss": 2.48,
|
| 32 |
+
"step": 16
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.64,
|
| 36 |
+
"learning_rate": 0.0003548387096774194,
|
| 37 |
+
"loss": 2.3692,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.77,
|
| 42 |
+
"learning_rate": 0.00022580645161290321,
|
| 43 |
+
"loss": 2.2791,
|
| 44 |
+
"step": 24
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9,
|
| 48 |
+
"learning_rate": 0.0006989247311827958,
|
| 49 |
+
"loss": 2.2783,
|
| 50 |
+
"step": 28
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_gen_len": 20.55,
|
| 55 |
+
"eval_loss": 2.021012306213379,
|
| 56 |
+
"eval_rouge1": 32.3793,
|
| 57 |
+
"eval_rouge2": 12.6427,
|
| 58 |
+
"eval_rougeL": 27.4027,
|
| 59 |
+
"eval_rougeLsum": 27.3,
|
| 60 |
+
"eval_runtime": 3629.2928,
|
| 61 |
+
"eval_samples_per_second": 0.028,
|
| 62 |
+
"eval_steps_per_second": 0.009,
|
| 63 |
+
"step": 31
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.03,
|
| 67 |
+
"learning_rate": 0.0006559139784946236,
|
| 68 |
+
"loss": 2.2677,
|
| 69 |
+
"step": 32
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.16,
|
| 73 |
+
"learning_rate": 0.0006129032258064516,
|
| 74 |
+
"loss": 1.8913,
|
| 75 |
+
"step": 36
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.29,
|
| 79 |
+
"learning_rate": 0.0005698924731182796,
|
| 80 |
+
"loss": 1.9234,
|
| 81 |
+
"step": 40
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.42,
|
| 85 |
+
"learning_rate": 0.0005268817204301075,
|
| 86 |
+
"loss": 1.8524,
|
| 87 |
+
"step": 44
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.55,
|
| 91 |
+
"learning_rate": 0.0004838709677419355,
|
| 92 |
+
"loss": 1.8549,
|
| 93 |
+
"step": 48
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.67,
|
| 97 |
+
"learning_rate": 0.00044086021505376343,
|
| 98 |
+
"loss": 1.9571,
|
| 99 |
+
"step": 52
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.8,
|
| 103 |
+
"learning_rate": 0.0003978494623655914,
|
| 104 |
+
"loss": 1.8606,
|
| 105 |
+
"step": 56
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.93,
|
| 109 |
+
"learning_rate": 0.0003548387096774194,
|
| 110 |
+
"loss": 1.791,
|
| 111 |
+
"step": 60
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0,
|
| 115 |
+
"eval_gen_len": 21.6,
|
| 116 |
+
"eval_loss": 1.9703446626663208,
|
| 117 |
+
"eval_rouge1": 34.5495,
|
| 118 |
+
"eval_rouge2": 12.6789,
|
| 119 |
+
"eval_rougeL": 28.3741,
|
| 120 |
+
"eval_rougeLsum": 28.4386,
|
| 121 |
+
"eval_runtime": 3780.972,
|
| 122 |
+
"eval_samples_per_second": 0.026,
|
| 123 |
+
"eval_steps_per_second": 0.009,
|
| 124 |
+
"step": 62
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.06,
|
| 128 |
+
"learning_rate": 0.0003118279569892473,
|
| 129 |
+
"loss": 1.7687,
|
| 130 |
+
"step": 64
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.19,
|
| 134 |
+
"learning_rate": 0.00026881720430107527,
|
| 135 |
+
"loss": 1.5525,
|
| 136 |
+
"step": 68
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"max_steps": 93,
|
| 140 |
+
"num_train_epochs": 3,
|
| 141 |
+
"total_flos": 1.813836532618199e+17,
|
| 142 |
+
"trial_name": null,
|
| 143 |
+
"trial_params": null
|
| 144 |
+
}
|