Commit
•
6c3031f
1
Parent(s):
be1c9a4
Upload 9 files
Browse files- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +114 -0
- training_args.bin +3 -0
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a3dbb3bd88bd07f2d3b97b3a7c94e357f113ade5ceb520ee9ddd53251661be
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d02bc189a0a2391884462b9b09af7f420de9a25ed4a6659ccf580ce6850a8e1
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2628040313720703,
|
| 3 |
+
"best_model_checkpoint": "test_trainer/checkpoint-6250",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 16.909454345703125,
|
| 14 |
+
"learning_rate": 4.866666666666667e-05,
|
| 15 |
+
"loss": 0.4174,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16,
|
| 20 |
+
"grad_norm": 5.426473617553711,
|
| 21 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 22 |
+
"loss": 0.3385,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24,
|
| 27 |
+
"grad_norm": 4.350019931793213,
|
| 28 |
+
"learning_rate": 4.600000000000001e-05,
|
| 29 |
+
"loss": 0.3105,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32,
|
| 34 |
+
"grad_norm": 5.816598892211914,
|
| 35 |
+
"learning_rate": 4.466666666666667e-05,
|
| 36 |
+
"loss": 0.3067,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4,
|
| 41 |
+
"grad_norm": 7.379697799682617,
|
| 42 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 43 |
+
"loss": 0.3019,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"grad_norm": 3.9567668437957764,
|
| 49 |
+
"learning_rate": 4.2e-05,
|
| 50 |
+
"loss": 0.2878,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"grad_norm": 20.508798599243164,
|
| 56 |
+
"learning_rate": 4.066666666666667e-05,
|
| 57 |
+
"loss": 0.3112,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.64,
|
| 62 |
+
"grad_norm": 0.06620893627405167,
|
| 63 |
+
"learning_rate": 3.933333333333333e-05,
|
| 64 |
+
"loss": 0.2922,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.72,
|
| 69 |
+
"grad_norm": 2.9895999431610107,
|
| 70 |
+
"learning_rate": 3.8e-05,
|
| 71 |
+
"loss": 0.2889,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8,
|
| 76 |
+
"grad_norm": 49.7801513671875,
|
| 77 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 78 |
+
"loss": 0.2787,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.88,
|
| 83 |
+
"grad_norm": 6.366118431091309,
|
| 84 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 85 |
+
"loss": 0.2764,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"grad_norm": 23.369661331176758,
|
| 91 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 92 |
+
"loss": 0.2859,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0,
|
| 97 |
+
"eval_accuracy": 0.9053,
|
| 98 |
+
"eval_loss": 0.2628040313720703,
|
| 99 |
+
"eval_runtime": 261.4897,
|
| 100 |
+
"eval_samples_per_second": 38.242,
|
| 101 |
+
"eval_steps_per_second": 4.78,
|
| 102 |
+
"step": 6250
|
| 103 |
+
}
|
| 104 |
+
],
|
| 105 |
+
"logging_steps": 500,
|
| 106 |
+
"max_steps": 18750,
|
| 107 |
+
"num_input_tokens_seen": 0,
|
| 108 |
+
"num_train_epochs": 3,
|
| 109 |
+
"save_steps": 500,
|
| 110 |
+
"total_flos": 1.31559071232e+16,
|
| 111 |
+
"train_batch_size": 8,
|
| 112 |
+
"trial_name": null,
|
| 113 |
+
"trial_params": null
|
| 114 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5321858afcafb121be6c585853b5decaa1ec5094adf12c3fd1aedd2f574a5d
|
| 3 |
+
size 4856
|