Training in progress, epoch 1
Browse files- all_results.json +9 -0
- model.safetensors +1 -1
- train_results.json +9 -0
- trainer_state.json +90 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.9828842929402675e+17,
|
| 4 |
+
"train_loss": 1.6144965134510645,
|
| 5 |
+
"train_runtime": 36481.981,
|
| 6 |
+
"train_samples": 193883,
|
| 7 |
+
"train_samples_per_second": 15.943,
|
| 8 |
+
"train_steps_per_second": 0.996
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 990348536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d01169a2d6ecd1212baf4930879bb674338c1b1955289e62abc06be1e926908
|
| 3 |
size 990348536
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.9828842929402675e+17,
|
| 4 |
+
"train_loss": 1.6144965134510645,
|
| 5 |
+
"train_runtime": 36481.981,
|
| 6 |
+
"train_samples": 193883,
|
| 7 |
+
"train_samples_per_second": 15.943,
|
| 8 |
+
"train_steps_per_second": 0.996
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 35.4918,
|
| 3 |
+
"best_model_checkpoint": "bin/liputan6-base/checkpoint-36354",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 36354,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.8706055879592896,
|
| 14 |
+
"learning_rate": 0.0006666666666666666,
|
| 15 |
+
"loss": 2.0683,
|
| 16 |
+
"step": 12118
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_gen_len": 38.11319722931098,
|
| 21 |
+
"eval_loss": 2.372281312942505,
|
| 22 |
+
"eval_rouge1": 33.423,
|
| 23 |
+
"eval_rouge2": 16.5875,
|
| 24 |
+
"eval_rougeL": 28.0723,
|
| 25 |
+
"eval_rougeLsum": 31.0371,
|
| 26 |
+
"eval_runtime": 1335.7227,
|
| 27 |
+
"eval_samples_per_second": 8.214,
|
| 28 |
+
"eval_steps_per_second": 0.129,
|
| 29 |
+
"step": 12118
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 0.7888175845146179,
|
| 34 |
+
"learning_rate": 0.0003333333333333333,
|
| 35 |
+
"loss": 1.5342,
|
| 36 |
+
"step": 24236
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_gen_len": 36.71764491432738,
|
| 41 |
+
"eval_loss": 2.139983654022217,
|
| 42 |
+
"eval_rouge1": 34.4775,
|
| 43 |
+
"eval_rouge2": 17.1757,
|
| 44 |
+
"eval_rougeL": 28.8546,
|
| 45 |
+
"eval_rougeLsum": 32.0264,
|
| 46 |
+
"eval_runtime": 1116.2631,
|
| 47 |
+
"eval_samples_per_second": 9.829,
|
| 48 |
+
"eval_steps_per_second": 0.154,
|
| 49 |
+
"step": 24236
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 0.6657369136810303,
|
| 54 |
+
"learning_rate": 0.0,
|
| 55 |
+
"loss": 1.241,
|
| 56 |
+
"step": 36354
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_gen_len": 36.4740247903755,
|
| 61 |
+
"eval_loss": 2.039839029312134,
|
| 62 |
+
"eval_rouge1": 35.4918,
|
| 63 |
+
"eval_rouge2": 17.885,
|
| 64 |
+
"eval_rougeL": 29.6804,
|
| 65 |
+
"eval_rougeLsum": 32.9507,
|
| 66 |
+
"eval_runtime": 1054.5787,
|
| 67 |
+
"eval_samples_per_second": 10.404,
|
| 68 |
+
"eval_steps_per_second": 0.163,
|
| 69 |
+
"step": 36354
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.0,
|
| 73 |
+
"step": 36354,
|
| 74 |
+
"total_flos": 3.9828842929402675e+17,
|
| 75 |
+
"train_loss": 1.6144965134510645,
|
| 76 |
+
"train_runtime": 36481.981,
|
| 77 |
+
"train_samples_per_second": 15.943,
|
| 78 |
+
"train_steps_per_second": 0.996
|
| 79 |
+
}
|
| 80 |
+
],
|
| 81 |
+
"logging_steps": 500,
|
| 82 |
+
"max_steps": 36354,
|
| 83 |
+
"num_input_tokens_seen": 0,
|
| 84 |
+
"num_train_epochs": 3,
|
| 85 |
+
"save_steps": 500,
|
| 86 |
+
"total_flos": 3.9828842929402675e+17,
|
| 87 |
+
"train_batch_size": 16,
|
| 88 |
+
"trial_name": null,
|
| 89 |
+
"trial_params": null
|
| 90 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4caf5727664b0a9127d4155c25dd62a1c519c7a98850d447fb40354f555cd16
|
| 3 |
size 5176
|