Upload with huggingface_hub
Browse files- config.json +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +694 -34
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -30,6 +30,6 @@
|
|
| 30 |
"sinusoidal_pos_embds": false,
|
| 31 |
"tie_weights_": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.
|
| 34 |
"vocab_size": 30522
|
| 35 |
}
|
|
|
|
| 30 |
"sinusoidal_pos_embds": false,
|
| 31 |
"tie_weights_": true,
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.22.1",
|
| 34 |
"vocab_size": 30522
|
| 35 |
}
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535706209
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:926621184a6b7a8ac5a4774f5c694efcbfc318bc5db3481564c2e2441ce39f30
|
| 3 |
size 535706209
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267857393
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7107ccbb7746e6dbde30bd9edb06601ecf5b7d95f0b337000cbae60a0f34cec
|
| 3 |
size 267857393
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24340d944dcaa627af1c5f51313a436ed4a3ad2a03a0651b1cd4a51bbe28284d
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5c9ed8372e0eec740369001de73734db6b5b259af9ae69a359108a1dd0fd17
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,105 +1,765 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
"epoch": 15.0,
|
| 5 |
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"
|
| 13 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"step": 200
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{
|
| 17 |
"epoch": 2.0,
|
| 18 |
-
"
|
| 19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"step": 400
|
| 21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
{
|
| 23 |
"epoch": 3.0,
|
| 24 |
-
"learning_rate": 1.
|
| 25 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"step": 600
|
| 27 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
{
|
| 29 |
"epoch": 4.0,
|
| 30 |
-
"
|
| 31 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"step": 800
|
| 33 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
{
|
| 35 |
"epoch": 5.0,
|
| 36 |
-
"
|
| 37 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
"step": 1000
|
| 39 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
{
|
| 41 |
"epoch": 6.0,
|
| 42 |
-
"learning_rate": 1.
|
| 43 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"step": 1200
|
| 45 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
{
|
| 47 |
"epoch": 7.0,
|
| 48 |
-
"
|
| 49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"step": 1400
|
| 51 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
{
|
| 53 |
"epoch": 8.0,
|
| 54 |
-
"
|
| 55 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"step": 1600
|
| 57 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
{
|
| 59 |
"epoch": 9.0,
|
| 60 |
-
"learning_rate": 1.
|
| 61 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"step": 1800
|
| 63 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
{
|
| 65 |
"epoch": 10.0,
|
| 66 |
-
"
|
| 67 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
"step": 2000
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{
|
| 71 |
"epoch": 11.0,
|
| 72 |
-
"
|
| 73 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
"step": 2200
|
| 75 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
{
|
| 77 |
"epoch": 12.0,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 2400
|
| 81 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
{
|
| 83 |
"epoch": 13.0,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 2600
|
| 87 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
{
|
| 89 |
"epoch": 14.0,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 2800
|
| 93 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
{
|
| 95 |
"epoch": 15.0,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
"step": 3000
|
| 99 |
}
|
| 100 |
],
|
| 101 |
-
"max_steps":
|
| 102 |
-
"num_train_epochs":
|
| 103 |
"total_flos": 6358548529152000.0,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5875,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-500",
|
| 4 |
"epoch": 15.0,
|
| 5 |
"global_step": 3000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.25,
|
| 12 |
+
"eval_accuracy": 0.5875,
|
| 13 |
+
"eval_latency_in_seconds": 0.016140898968749935,
|
| 14 |
+
"eval_loss": 1.0195873975753784,
|
| 15 |
+
"eval_runtime": 37.9935,
|
| 16 |
+
"eval_samples_per_second": 21.056,
|
| 17 |
+
"eval_steps_per_second": 1.316,
|
| 18 |
+
"eval_total_time_in_seconds": 12.91271917499995,
|
| 19 |
+
"step": 50
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.5,
|
| 23 |
+
"eval_accuracy": 0.5875,
|
| 24 |
+
"eval_latency_in_seconds": 0.016577634310000065,
|
| 25 |
+
"eval_loss": 0.9936361908912659,
|
| 26 |
+
"eval_runtime": 30.0792,
|
| 27 |
+
"eval_samples_per_second": 26.596,
|
| 28 |
+
"eval_steps_per_second": 1.662,
|
| 29 |
+
"eval_total_time_in_seconds": 13.262107448000052,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.75,
|
| 34 |
+
"eval_accuracy": 0.5875,
|
| 35 |
+
"eval_latency_in_seconds": 0.016618314516250052,
|
| 36 |
+
"eval_loss": 1.0124518871307373,
|
| 37 |
+
"eval_runtime": 29.9038,
|
| 38 |
+
"eval_samples_per_second": 26.752,
|
| 39 |
+
"eval_steps_per_second": 1.672,
|
| 40 |
+
"eval_total_time_in_seconds": 13.294651613000042,
|
| 41 |
+
"step": 150
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.0,
|
| 45 |
+
"learning_rate": 1.9e-05,
|
| 46 |
+
"loss": 1.007,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
{
|
| 50 |
"epoch": 1.0,
|
| 51 |
+
"eval_accuracy": 0.5875,
|
| 52 |
+
"eval_latency_in_seconds": 0.01668884421499996,
|
| 53 |
+
"eval_loss": 1.0121251344680786,
|
| 54 |
+
"eval_runtime": 29.8443,
|
| 55 |
+
"eval_samples_per_second": 26.806,
|
| 56 |
+
"eval_steps_per_second": 1.675,
|
| 57 |
+
"eval_total_time_in_seconds": 13.351075371999968,
|
| 58 |
"step": 200
|
| 59 |
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.25,
|
| 62 |
+
"eval_accuracy": 0.5875,
|
| 63 |
+
"eval_latency_in_seconds": 0.016656154167500006,
|
| 64 |
+
"eval_loss": 0.9109314680099487,
|
| 65 |
+
"eval_runtime": 29.8759,
|
| 66 |
+
"eval_samples_per_second": 26.777,
|
| 67 |
+
"eval_steps_per_second": 1.674,
|
| 68 |
+
"eval_total_time_in_seconds": 13.324923334000005,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.5,
|
| 73 |
+
"eval_accuracy": 0.5875,
|
| 74 |
+
"eval_latency_in_seconds": 0.016652411622499984,
|
| 75 |
+
"eval_loss": 0.8836429119110107,
|
| 76 |
+
"eval_runtime": 29.8232,
|
| 77 |
+
"eval_samples_per_second": 26.825,
|
| 78 |
+
"eval_steps_per_second": 1.677,
|
| 79 |
+
"eval_total_time_in_seconds": 13.321929297999986,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.75,
|
| 84 |
+
"eval_accuracy": 0.5875,
|
| 85 |
+
"eval_latency_in_seconds": 0.016655641563749983,
|
| 86 |
+
"eval_loss": 0.8780828714370728,
|
| 87 |
+
"eval_runtime": 29.9106,
|
| 88 |
+
"eval_samples_per_second": 26.746,
|
| 89 |
+
"eval_steps_per_second": 1.672,
|
| 90 |
+
"eval_total_time_in_seconds": 13.324513250999985,
|
| 91 |
+
"step": 350
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 2.0,
|
| 95 |
+
"learning_rate": 1.8e-05,
|
| 96 |
+
"loss": 0.8906,
|
| 97 |
+
"step": 400
|
| 98 |
+
},
|
| 99 |
{
|
| 100 |
"epoch": 2.0,
|
| 101 |
+
"eval_accuracy": 0.5875,
|
| 102 |
+
"eval_latency_in_seconds": 0.016710829281249884,
|
| 103 |
+
"eval_loss": 0.844797670841217,
|
| 104 |
+
"eval_runtime": 29.9696,
|
| 105 |
+
"eval_samples_per_second": 26.694,
|
| 106 |
+
"eval_steps_per_second": 1.668,
|
| 107 |
+
"eval_total_time_in_seconds": 13.368663424999909,
|
| 108 |
"step": 400
|
| 109 |
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.25,
|
| 112 |
+
"eval_accuracy": 0.5875,
|
| 113 |
+
"eval_latency_in_seconds": 0.016734712483749945,
|
| 114 |
+
"eval_loss": 0.8375944495201111,
|
| 115 |
+
"eval_runtime": 29.9532,
|
| 116 |
+
"eval_samples_per_second": 26.708,
|
| 117 |
+
"eval_steps_per_second": 1.669,
|
| 118 |
+
"eval_total_time_in_seconds": 13.387769986999956,
|
| 119 |
+
"step": 450
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.5,
|
| 123 |
+
"eval_accuracy": 0.5875,
|
| 124 |
+
"eval_latency_in_seconds": 0.016665541630000006,
|
| 125 |
+
"eval_loss": 0.828183114528656,
|
| 126 |
+
"eval_runtime": 29.8508,
|
| 127 |
+
"eval_samples_per_second": 26.8,
|
| 128 |
+
"eval_steps_per_second": 1.675,
|
| 129 |
+
"eval_total_time_in_seconds": 13.332433304000006,
|
| 130 |
+
"step": 500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.75,
|
| 134 |
+
"eval_accuracy": 0.5875,
|
| 135 |
+
"eval_latency_in_seconds": 0.01663229147999999,
|
| 136 |
+
"eval_loss": 0.8245559930801392,
|
| 137 |
+
"eval_runtime": 29.8164,
|
| 138 |
+
"eval_samples_per_second": 26.831,
|
| 139 |
+
"eval_steps_per_second": 1.677,
|
| 140 |
+
"eval_total_time_in_seconds": 13.305833183999994,
|
| 141 |
+
"step": 550
|
| 142 |
+
},
|
| 143 |
{
|
| 144 |
"epoch": 3.0,
|
| 145 |
+
"learning_rate": 1.7e-05,
|
| 146 |
+
"loss": 0.7455,
|
| 147 |
+
"step": 600
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.0,
|
| 151 |
+
"eval_accuracy": 0.5875,
|
| 152 |
+
"eval_latency_in_seconds": 0.01658837374625023,
|
| 153 |
+
"eval_loss": 0.8258004784584045,
|
| 154 |
+
"eval_runtime": 29.782,
|
| 155 |
+
"eval_samples_per_second": 26.862,
|
| 156 |
+
"eval_steps_per_second": 1.679,
|
| 157 |
+
"eval_total_time_in_seconds": 13.270698997000181,
|
| 158 |
"step": 600
|
| 159 |
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.25,
|
| 162 |
+
"eval_accuracy": 0.5875,
|
| 163 |
+
"eval_latency_in_seconds": 0.016743442093749936,
|
| 164 |
+
"eval_loss": 0.8827661275863647,
|
| 165 |
+
"eval_runtime": 30.0887,
|
| 166 |
+
"eval_samples_per_second": 26.588,
|
| 167 |
+
"eval_steps_per_second": 1.662,
|
| 168 |
+
"eval_total_time_in_seconds": 13.394753674999947,
|
| 169 |
+
"step": 650
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.5,
|
| 173 |
+
"eval_accuracy": 0.5875,
|
| 174 |
+
"eval_latency_in_seconds": 0.01667224465624997,
|
| 175 |
+
"eval_loss": 0.8894978165626526,
|
| 176 |
+
"eval_runtime": 30.1041,
|
| 177 |
+
"eval_samples_per_second": 26.574,
|
| 178 |
+
"eval_steps_per_second": 1.661,
|
| 179 |
+
"eval_total_time_in_seconds": 13.337795724999978,
|
| 180 |
+
"step": 700
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.75,
|
| 184 |
+
"eval_accuracy": 0.5875,
|
| 185 |
+
"eval_latency_in_seconds": 0.016693762731250103,
|
| 186 |
+
"eval_loss": 0.9063799381256104,
|
| 187 |
+
"eval_runtime": 29.8535,
|
| 188 |
+
"eval_samples_per_second": 26.797,
|
| 189 |
+
"eval_steps_per_second": 1.675,
|
| 190 |
+
"eval_total_time_in_seconds": 13.355010185000083,
|
| 191 |
+
"step": 750
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.0,
|
| 195 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 196 |
+
"loss": 0.549,
|
| 197 |
+
"step": 800
|
| 198 |
+
},
|
| 199 |
{
|
| 200 |
"epoch": 4.0,
|
| 201 |
+
"eval_accuracy": 0.5875,
|
| 202 |
+
"eval_latency_in_seconds": 0.016649374238749886,
|
| 203 |
+
"eval_loss": 0.9239490032196045,
|
| 204 |
+
"eval_runtime": 29.9071,
|
| 205 |
+
"eval_samples_per_second": 26.749,
|
| 206 |
+
"eval_steps_per_second": 1.672,
|
| 207 |
+
"eval_total_time_in_seconds": 13.319499390999908,
|
| 208 |
"step": 800
|
| 209 |
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.25,
|
| 212 |
+
"eval_accuracy": 0.5875,
|
| 213 |
+
"eval_latency_in_seconds": 0.01666813849999983,
|
| 214 |
+
"eval_loss": 0.9834891557693481,
|
| 215 |
+
"eval_runtime": 29.9398,
|
| 216 |
+
"eval_samples_per_second": 26.72,
|
| 217 |
+
"eval_steps_per_second": 1.67,
|
| 218 |
+
"eval_total_time_in_seconds": 13.334510799999862,
|
| 219 |
+
"step": 850
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.5,
|
| 223 |
+
"eval_accuracy": 0.5875,
|
| 224 |
+
"eval_latency_in_seconds": 0.01672061295875011,
|
| 225 |
+
"eval_loss": 1.0434612035751343,
|
| 226 |
+
"eval_runtime": 30.0191,
|
| 227 |
+
"eval_samples_per_second": 26.65,
|
| 228 |
+
"eval_steps_per_second": 1.666,
|
| 229 |
+
"eval_total_time_in_seconds": 13.376490367000088,
|
| 230 |
+
"step": 900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.75,
|
| 234 |
+
"eval_accuracy": 0.5875,
|
| 235 |
+
"eval_latency_in_seconds": 0.016696340333749903,
|
| 236 |
+
"eval_loss": 1.0434249639511108,
|
| 237 |
+
"eval_runtime": 30.0388,
|
| 238 |
+
"eval_samples_per_second": 26.632,
|
| 239 |
+
"eval_steps_per_second": 1.665,
|
| 240 |
+
"eval_total_time_in_seconds": 13.357072266999921,
|
| 241 |
+
"step": 950
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 5.0,
|
| 245 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 246 |
+
"loss": 0.37,
|
| 247 |
+
"step": 1000
|
| 248 |
+
},
|
| 249 |
{
|
| 250 |
"epoch": 5.0,
|
| 251 |
+
"eval_accuracy": 0.5875,
|
| 252 |
+
"eval_latency_in_seconds": 0.01674834000874995,
|
| 253 |
+
"eval_loss": 1.0716580152511597,
|
| 254 |
+
"eval_runtime": 30.0668,
|
| 255 |
+
"eval_samples_per_second": 26.607,
|
| 256 |
+
"eval_steps_per_second": 1.663,
|
| 257 |
+
"eval_total_time_in_seconds": 13.39867200699996,
|
| 258 |
"step": 1000
|
| 259 |
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.25,
|
| 262 |
+
"eval_accuracy": 0.5875,
|
| 263 |
+
"eval_latency_in_seconds": 0.01658757922625,
|
| 264 |
+
"eval_loss": 1.1702197790145874,
|
| 265 |
+
"eval_runtime": 29.7005,
|
| 266 |
+
"eval_samples_per_second": 26.936,
|
| 267 |
+
"eval_steps_per_second": 1.683,
|
| 268 |
+
"eval_total_time_in_seconds": 13.270063381,
|
| 269 |
+
"step": 1050
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.5,
|
| 273 |
+
"eval_accuracy": 0.5875,
|
| 274 |
+
"eval_latency_in_seconds": 0.016588210039999753,
|
| 275 |
+
"eval_loss": 1.363202691078186,
|
| 276 |
+
"eval_runtime": 29.7061,
|
| 277 |
+
"eval_samples_per_second": 26.931,
|
| 278 |
+
"eval_steps_per_second": 1.683,
|
| 279 |
+
"eval_total_time_in_seconds": 13.270568031999801,
|
| 280 |
+
"step": 1100
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.75,
|
| 284 |
+
"eval_accuracy": 0.5875,
|
| 285 |
+
"eval_latency_in_seconds": 0.016613341418749882,
|
| 286 |
+
"eval_loss": 1.3025741577148438,
|
| 287 |
+
"eval_runtime": 29.8243,
|
| 288 |
+
"eval_samples_per_second": 26.824,
|
| 289 |
+
"eval_steps_per_second": 1.676,
|
| 290 |
+
"eval_total_time_in_seconds": 13.290673134999906,
|
| 291 |
+
"step": 1150
|
| 292 |
+
},
|
| 293 |
{
|
| 294 |
"epoch": 6.0,
|
| 295 |
+
"learning_rate": 1.4e-05,
|
| 296 |
+
"loss": 0.231,
|
| 297 |
+
"step": 1200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 6.0,
|
| 301 |
+
"eval_accuracy": 0.5875,
|
| 302 |
+
"eval_latency_in_seconds": 0.016670319153750484,
|
| 303 |
+
"eval_loss": 1.241083025932312,
|
| 304 |
+
"eval_runtime": 29.8584,
|
| 305 |
+
"eval_samples_per_second": 26.793,
|
| 306 |
+
"eval_steps_per_second": 1.675,
|
| 307 |
+
"eval_total_time_in_seconds": 13.336255323000387,
|
| 308 |
"step": 1200
|
| 309 |
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.25,
|
| 312 |
+
"eval_accuracy": 0.5875,
|
| 313 |
+
"eval_latency_in_seconds": 0.01664680648125,
|
| 314 |
+
"eval_loss": 1.3705066442489624,
|
| 315 |
+
"eval_runtime": 29.9316,
|
| 316 |
+
"eval_samples_per_second": 26.728,
|
| 317 |
+
"eval_steps_per_second": 1.67,
|
| 318 |
+
"eval_total_time_in_seconds": 13.317445184999997,
|
| 319 |
+
"step": 1250
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 6.5,
|
| 323 |
+
"eval_accuracy": 0.5875,
|
| 324 |
+
"eval_latency_in_seconds": 0.01666591738875013,
|
| 325 |
+
"eval_loss": 1.5176929235458374,
|
| 326 |
+
"eval_runtime": 29.9921,
|
| 327 |
+
"eval_samples_per_second": 26.674,
|
| 328 |
+
"eval_steps_per_second": 1.667,
|
| 329 |
+
"eval_total_time_in_seconds": 13.332733911000105,
|
| 330 |
+
"step": 1300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 6.75,
|
| 334 |
+
"eval_accuracy": 0.5875,
|
| 335 |
+
"eval_latency_in_seconds": 0.016700183542499757,
|
| 336 |
+
"eval_loss": 1.8310248851776123,
|
| 337 |
+
"eval_runtime": 29.9705,
|
| 338 |
+
"eval_samples_per_second": 26.693,
|
| 339 |
+
"eval_steps_per_second": 1.668,
|
| 340 |
+
"eval_total_time_in_seconds": 13.360146833999806,
|
| 341 |
+
"step": 1350
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 7.0,
|
| 345 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 346 |
+
"loss": 0.1348,
|
| 347 |
+
"step": 1400
|
| 348 |
+
},
|
| 349 |
{
|
| 350 |
"epoch": 7.0,
|
| 351 |
+
"eval_accuracy": 0.5875,
|
| 352 |
+
"eval_latency_in_seconds": 0.016722027651250075,
|
| 353 |
+
"eval_loss": 1.6683160066604614,
|
| 354 |
+
"eval_runtime": 30.0677,
|
| 355 |
+
"eval_samples_per_second": 26.607,
|
| 356 |
+
"eval_steps_per_second": 1.663,
|
| 357 |
+
"eval_total_time_in_seconds": 13.377622121000059,
|
| 358 |
"step": 1400
|
| 359 |
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.25,
|
| 362 |
+
"eval_accuracy": 0.5875,
|
| 363 |
+
"eval_latency_in_seconds": 0.016639053724999825,
|
| 364 |
+
"eval_loss": 1.8127371072769165,
|
| 365 |
+
"eval_runtime": 29.9019,
|
| 366 |
+
"eval_samples_per_second": 26.754,
|
| 367 |
+
"eval_steps_per_second": 1.672,
|
| 368 |
+
"eval_total_time_in_seconds": 13.31124297999986,
|
| 369 |
+
"step": 1450
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 7.5,
|
| 373 |
+
"eval_accuracy": 0.5875,
|
| 374 |
+
"eval_latency_in_seconds": 0.016672658619999652,
|
| 375 |
+
"eval_loss": 1.8947601318359375,
|
| 376 |
+
"eval_runtime": 29.8732,
|
| 377 |
+
"eval_samples_per_second": 26.78,
|
| 378 |
+
"eval_steps_per_second": 1.674,
|
| 379 |
+
"eval_total_time_in_seconds": 13.338126895999721,
|
| 380 |
+
"step": 1500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.75,
|
| 384 |
+
"eval_accuracy": 0.5875,
|
| 385 |
+
"eval_latency_in_seconds": 0.016528693013750057,
|
| 386 |
+
"eval_loss": 1.9334509372711182,
|
| 387 |
+
"eval_runtime": 29.6754,
|
| 388 |
+
"eval_samples_per_second": 26.958,
|
| 389 |
+
"eval_steps_per_second": 1.685,
|
| 390 |
+
"eval_total_time_in_seconds": 13.222954411000046,
|
| 391 |
+
"step": 1550
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 8.0,
|
| 395 |
+
"learning_rate": 1.2e-05,
|
| 396 |
+
"loss": 0.0896,
|
| 397 |
+
"step": 1600
|
| 398 |
+
},
|
| 399 |
{
|
| 400 |
"epoch": 8.0,
|
| 401 |
+
"eval_accuracy": 0.5875,
|
| 402 |
+
"eval_latency_in_seconds": 0.016713374875000114,
|
| 403 |
+
"eval_loss": 1.8743096590042114,
|
| 404 |
+
"eval_runtime": 29.9755,
|
| 405 |
+
"eval_samples_per_second": 26.688,
|
| 406 |
+
"eval_steps_per_second": 1.668,
|
| 407 |
+
"eval_total_time_in_seconds": 13.37069990000009,
|
| 408 |
"step": 1600
|
| 409 |
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 8.25,
|
| 412 |
+
"eval_accuracy": 0.5875,
|
| 413 |
+
"eval_latency_in_seconds": 0.01665160638624968,
|
| 414 |
+
"eval_loss": 1.999316692352295,
|
| 415 |
+
"eval_runtime": 29.865,
|
| 416 |
+
"eval_samples_per_second": 26.787,
|
| 417 |
+
"eval_steps_per_second": 1.674,
|
| 418 |
+
"eval_total_time_in_seconds": 13.321285108999746,
|
| 419 |
+
"step": 1650
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 8.5,
|
| 423 |
+
"eval_accuracy": 0.5875,
|
| 424 |
+
"eval_latency_in_seconds": 0.016658729771249912,
|
| 425 |
+
"eval_loss": 2.0449576377868652,
|
| 426 |
+
"eval_runtime": 29.8258,
|
| 427 |
+
"eval_samples_per_second": 26.822,
|
| 428 |
+
"eval_steps_per_second": 1.676,
|
| 429 |
+
"eval_total_time_in_seconds": 13.326983816999928,
|
| 430 |
+
"step": 1700
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 8.75,
|
| 434 |
+
"eval_accuracy": 0.5875,
|
| 435 |
+
"eval_latency_in_seconds": 0.016647704048749573,
|
| 436 |
+
"eval_loss": 2.0946853160858154,
|
| 437 |
+
"eval_runtime": 29.8963,
|
| 438 |
+
"eval_samples_per_second": 26.759,
|
| 439 |
+
"eval_steps_per_second": 1.672,
|
| 440 |
+
"eval_total_time_in_seconds": 13.31816323899966,
|
| 441 |
+
"step": 1750
|
| 442 |
+
},
|
| 443 |
{
|
| 444 |
"epoch": 9.0,
|
| 445 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 446 |
+
"loss": 0.0599,
|
| 447 |
+
"step": 1800
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.0,
|
| 451 |
+
"eval_accuracy": 0.5875,
|
| 452 |
+
"eval_latency_in_seconds": 0.016691148148750015,
|
| 453 |
+
"eval_loss": 2.231701612472534,
|
| 454 |
+
"eval_runtime": 30.1095,
|
| 455 |
+
"eval_samples_per_second": 26.57,
|
| 456 |
+
"eval_steps_per_second": 1.661,
|
| 457 |
+
"eval_total_time_in_seconds": 13.352918519000013,
|
| 458 |
"step": 1800
|
| 459 |
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 9.25,
|
| 462 |
+
"eval_accuracy": 0.5875,
|
| 463 |
+
"eval_latency_in_seconds": 0.0166487254499998,
|
| 464 |
+
"eval_loss": 2.204172134399414,
|
| 465 |
+
"eval_runtime": 29.9643,
|
| 466 |
+
"eval_samples_per_second": 26.698,
|
| 467 |
+
"eval_steps_per_second": 1.669,
|
| 468 |
+
"eval_total_time_in_seconds": 13.318980359999841,
|
| 469 |
+
"step": 1850
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 9.5,
|
| 473 |
+
"eval_accuracy": 0.5875,
|
| 474 |
+
"eval_latency_in_seconds": 0.016727415717500093,
|
| 475 |
+
"eval_loss": 2.282806396484375,
|
| 476 |
+
"eval_runtime": 30.0555,
|
| 477 |
+
"eval_samples_per_second": 26.617,
|
| 478 |
+
"eval_steps_per_second": 1.664,
|
| 479 |
+
"eval_total_time_in_seconds": 13.381932574000075,
|
| 480 |
+
"step": 1900
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 9.75,
|
| 484 |
+
"eval_accuracy": 0.5875,
|
| 485 |
+
"eval_latency_in_seconds": 0.0166388489374998,
|
| 486 |
+
"eval_loss": 2.298581123352051,
|
| 487 |
+
"eval_runtime": 29.9445,
|
| 488 |
+
"eval_samples_per_second": 26.716,
|
| 489 |
+
"eval_steps_per_second": 1.67,
|
| 490 |
+
"eval_total_time_in_seconds": 13.311079149999841,
|
| 491 |
+
"step": 1950
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 10.0,
|
| 495 |
+
"learning_rate": 1e-05,
|
| 496 |
+
"loss": 0.0495,
|
| 497 |
+
"step": 2000
|
| 498 |
+
},
|
| 499 |
{
|
| 500 |
"epoch": 10.0,
|
| 501 |
+
"eval_accuracy": 0.5875,
|
| 502 |
+
"eval_latency_in_seconds": 0.01665341812874999,
|
| 503 |
+
"eval_loss": 2.227576494216919,
|
| 504 |
+
"eval_runtime": 29.8758,
|
| 505 |
+
"eval_samples_per_second": 26.777,
|
| 506 |
+
"eval_steps_per_second": 1.674,
|
| 507 |
+
"eval_total_time_in_seconds": 13.322734502999992,
|
| 508 |
"step": 2000
|
| 509 |
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 10.25,
|
| 512 |
+
"eval_accuracy": 0.5875,
|
| 513 |
+
"eval_latency_in_seconds": 0.016612832117500035,
|
| 514 |
+
"eval_loss": 2.2979378700256348,
|
| 515 |
+
"eval_runtime": 29.8189,
|
| 516 |
+
"eval_samples_per_second": 26.829,
|
| 517 |
+
"eval_steps_per_second": 1.677,
|
| 518 |
+
"eval_total_time_in_seconds": 13.290265694000027,
|
| 519 |
+
"step": 2050
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.5,
|
| 523 |
+
"eval_accuracy": 0.5875,
|
| 524 |
+
"eval_latency_in_seconds": 0.016637017281250336,
|
| 525 |
+
"eval_loss": 2.284951686859131,
|
| 526 |
+
"eval_runtime": 29.8695,
|
| 527 |
+
"eval_samples_per_second": 26.783,
|
| 528 |
+
"eval_steps_per_second": 1.674,
|
| 529 |
+
"eval_total_time_in_seconds": 13.30961382500027,
|
| 530 |
+
"step": 2100
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 10.75,
|
| 534 |
+
"eval_accuracy": 0.5875,
|
| 535 |
+
"eval_latency_in_seconds": 0.016614138501249726,
|
| 536 |
+
"eval_loss": 2.3448538780212402,
|
| 537 |
+
"eval_runtime": 29.8656,
|
| 538 |
+
"eval_samples_per_second": 26.787,
|
| 539 |
+
"eval_steps_per_second": 1.674,
|
| 540 |
+
"eval_total_time_in_seconds": 13.291310800999781,
|
| 541 |
+
"step": 2150
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 11.0,
|
| 545 |
+
"learning_rate": 9e-06,
|
| 546 |
+
"loss": 0.0276,
|
| 547 |
+
"step": 2200
|
| 548 |
+
},
|
| 549 |
{
|
| 550 |
"epoch": 11.0,
|
| 551 |
+
"eval_accuracy": 0.5875,
|
| 552 |
+
"eval_latency_in_seconds": 0.016691225096250265,
|
| 553 |
+
"eval_loss": 2.307952880859375,
|
| 554 |
+
"eval_runtime": 29.8828,
|
| 555 |
+
"eval_samples_per_second": 26.771,
|
| 556 |
+
"eval_steps_per_second": 1.673,
|
| 557 |
+
"eval_total_time_in_seconds": 13.352980077000211,
|
| 558 |
"step": 2200
|
| 559 |
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 11.25,
|
| 562 |
+
"eval_accuracy": 0.5875,
|
| 563 |
+
"eval_latency_in_seconds": 0.01659034708999968,
|
| 564 |
+
"eval_loss": 2.3699042797088623,
|
| 565 |
+
"eval_runtime": 29.8101,
|
| 566 |
+
"eval_samples_per_second": 26.837,
|
| 567 |
+
"eval_steps_per_second": 1.677,
|
| 568 |
+
"eval_total_time_in_seconds": 13.272277671999746,
|
| 569 |
+
"step": 2250
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 11.5,
|
| 573 |
+
"eval_accuracy": 0.5875,
|
| 574 |
+
"eval_latency_in_seconds": 0.01659643314749985,
|
| 575 |
+
"eval_loss": 2.4644832611083984,
|
| 576 |
+
"eval_runtime": 29.8395,
|
| 577 |
+
"eval_samples_per_second": 26.81,
|
| 578 |
+
"eval_steps_per_second": 1.676,
|
| 579 |
+
"eval_total_time_in_seconds": 13.277146517999881,
|
| 580 |
+
"step": 2300
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 11.75,
|
| 584 |
+
"eval_accuracy": 0.5875,
|
| 585 |
+
"eval_latency_in_seconds": 0.016764325188750036,
|
| 586 |
+
"eval_loss": 2.4088258743286133,
|
| 587 |
+
"eval_runtime": 30.0842,
|
| 588 |
+
"eval_samples_per_second": 26.592,
|
| 589 |
+
"eval_steps_per_second": 1.662,
|
| 590 |
+
"eval_total_time_in_seconds": 13.411460151000028,
|
| 591 |
+
"step": 2350
|
| 592 |
+
},
|
| 593 |
{
|
| 594 |
"epoch": 12.0,
|
| 595 |
+
"learning_rate": 8.000000000000001e-06,
|
| 596 |
+
"loss": 0.0131,
|
| 597 |
"step": 2400
|
| 598 |
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 12.0,
|
| 601 |
+
"eval_accuracy": 0.5875,
|
| 602 |
+
"eval_latency_in_seconds": 0.016665852497500282,
|
| 603 |
+
"eval_loss": 2.4499921798706055,
|
| 604 |
+
"eval_runtime": 29.9819,
|
| 605 |
+
"eval_samples_per_second": 26.683,
|
| 606 |
+
"eval_steps_per_second": 1.668,
|
| 607 |
+
"eval_total_time_in_seconds": 13.332681998000226,
|
| 608 |
+
"step": 2400
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 12.25,
|
| 612 |
+
"eval_accuracy": 0.5875,
|
| 613 |
+
"eval_latency_in_seconds": 0.01666696527499994,
|
| 614 |
+
"eval_loss": 2.471630096435547,
|
| 615 |
+
"eval_runtime": 29.8811,
|
| 616 |
+
"eval_samples_per_second": 26.773,
|
| 617 |
+
"eval_steps_per_second": 1.673,
|
| 618 |
+
"eval_total_time_in_seconds": 13.333572219999951,
|
| 619 |
+
"step": 2450
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 12.5,
|
| 623 |
+
"eval_accuracy": 0.5875,
|
| 624 |
+
"eval_latency_in_seconds": 0.016629205762500307,
|
| 625 |
+
"eval_loss": 2.5404670238494873,
|
| 626 |
+
"eval_runtime": 29.8336,
|
| 627 |
+
"eval_samples_per_second": 26.815,
|
| 628 |
+
"eval_steps_per_second": 1.676,
|
| 629 |
+
"eval_total_time_in_seconds": 13.303364610000244,
|
| 630 |
+
"step": 2500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 12.75,
|
| 634 |
+
"eval_accuracy": 0.5875,
|
| 635 |
+
"eval_latency_in_seconds": 0.016587090722500763,
|
| 636 |
+
"eval_loss": 2.5341074466705322,
|
| 637 |
+
"eval_runtime": 29.8717,
|
| 638 |
+
"eval_samples_per_second": 26.781,
|
| 639 |
+
"eval_steps_per_second": 1.674,
|
| 640 |
+
"eval_total_time_in_seconds": 13.269672578000609,
|
| 641 |
+
"step": 2550
|
| 642 |
+
},
|
| 643 |
{
|
| 644 |
"epoch": 13.0,
|
| 645 |
+
"learning_rate": 7e-06,
|
| 646 |
+
"loss": 0.0127,
|
| 647 |
"step": 2600
|
| 648 |
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 13.0,
|
| 651 |
+
"eval_accuracy": 0.5875,
|
| 652 |
+
"eval_latency_in_seconds": 0.016596427140000286,
|
| 653 |
+
"eval_loss": 2.550121784210205,
|
| 654 |
+
"eval_runtime": 29.7591,
|
| 655 |
+
"eval_samples_per_second": 26.883,
|
| 656 |
+
"eval_steps_per_second": 1.68,
|
| 657 |
+
"eval_total_time_in_seconds": 13.27714171200023,
|
| 658 |
+
"step": 2600
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 13.25,
|
| 662 |
+
"eval_accuracy": 0.5875,
|
| 663 |
+
"eval_latency_in_seconds": 0.01661448852124977,
|
| 664 |
+
"eval_loss": 2.5775039196014404,
|
| 665 |
+
"eval_runtime": 29.7738,
|
| 666 |
+
"eval_samples_per_second": 26.869,
|
| 667 |
+
"eval_steps_per_second": 1.679,
|
| 668 |
+
"eval_total_time_in_seconds": 13.291590816999815,
|
| 669 |
+
"step": 2650
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 13.5,
|
| 673 |
+
"eval_accuracy": 0.5875,
|
| 674 |
+
"eval_latency_in_seconds": 0.01660655404249951,
|
| 675 |
+
"eval_loss": 2.5819220542907715,
|
| 676 |
+
"eval_runtime": 29.8343,
|
| 677 |
+
"eval_samples_per_second": 26.815,
|
| 678 |
+
"eval_steps_per_second": 1.676,
|
| 679 |
+
"eval_total_time_in_seconds": 13.285243233999608,
|
| 680 |
+
"step": 2700
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 13.75,
|
| 684 |
+
"eval_accuracy": 0.5875,
|
| 685 |
+
"eval_latency_in_seconds": 0.01656317381874942,
|
| 686 |
+
"eval_loss": 2.562864303588867,
|
| 687 |
+
"eval_runtime": 29.749,
|
| 688 |
+
"eval_samples_per_second": 26.892,
|
| 689 |
+
"eval_steps_per_second": 1.681,
|
| 690 |
+
"eval_total_time_in_seconds": 13.250539054999535,
|
| 691 |
+
"step": 2750
|
| 692 |
+
},
|
| 693 |
{
|
| 694 |
"epoch": 14.0,
|
| 695 |
+
"learning_rate": 6e-06,
|
| 696 |
+
"loss": 0.0112,
|
| 697 |
"step": 2800
|
| 698 |
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 14.0,
|
| 701 |
+
"eval_accuracy": 0.5875,
|
| 702 |
+
"eval_latency_in_seconds": 0.016711680048749712,
|
| 703 |
+
"eval_loss": 2.6634762287139893,
|
| 704 |
+
"eval_runtime": 30.0388,
|
| 705 |
+
"eval_samples_per_second": 26.632,
|
| 706 |
+
"eval_steps_per_second": 1.665,
|
| 707 |
+
"eval_total_time_in_seconds": 13.36934403899977,
|
| 708 |
+
"step": 2800
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 14.25,
|
| 712 |
+
"eval_accuracy": 0.5875,
|
| 713 |
+
"eval_latency_in_seconds": 0.01673866046249941,
|
| 714 |
+
"eval_loss": 2.649559259414673,
|
| 715 |
+
"eval_runtime": 30.035,
|
| 716 |
+
"eval_samples_per_second": 26.636,
|
| 717 |
+
"eval_steps_per_second": 1.665,
|
| 718 |
+
"eval_total_time_in_seconds": 13.390928369999529,
|
| 719 |
+
"step": 2850
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 14.5,
|
| 723 |
+
"eval_accuracy": 0.5875,
|
| 724 |
+
"eval_latency_in_seconds": 0.016693803422499515,
|
| 725 |
+
"eval_loss": 2.6672680377960205,
|
| 726 |
+
"eval_runtime": 29.947,
|
| 727 |
+
"eval_samples_per_second": 26.714,
|
| 728 |
+
"eval_steps_per_second": 1.67,
|
| 729 |
+
"eval_total_time_in_seconds": 13.35504273799961,
|
| 730 |
+
"step": 2900
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 14.75,
|
| 734 |
+
"eval_accuracy": 0.5875,
|
| 735 |
+
"eval_latency_in_seconds": 0.016712438349999276,
|
| 736 |
+
"eval_loss": 2.7292675971984863,
|
| 737 |
+
"eval_runtime": 29.9456,
|
| 738 |
+
"eval_samples_per_second": 26.715,
|
| 739 |
+
"eval_steps_per_second": 1.67,
|
| 740 |
+
"eval_total_time_in_seconds": 13.36995067999942,
|
| 741 |
+
"step": 2950
|
| 742 |
+
},
|
| 743 |
{
|
| 744 |
"epoch": 15.0,
|
| 745 |
+
"learning_rate": 5e-06,
|
| 746 |
+
"loss": 0.0108,
|
| 747 |
+
"step": 3000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 15.0,
|
| 751 |
+
"eval_accuracy": 0.5875,
|
| 752 |
+
"eval_latency_in_seconds": 0.016635910904999492,
|
| 753 |
+
"eval_loss": 2.664646625518799,
|
| 754 |
+
"eval_runtime": 29.8887,
|
| 755 |
+
"eval_samples_per_second": 26.766,
|
| 756 |
+
"eval_steps_per_second": 1.673,
|
| 757 |
+
"eval_total_time_in_seconds": 13.308728723999593,
|
| 758 |
"step": 3000
|
| 759 |
}
|
| 760 |
],
|
| 761 |
+
"max_steps": 4000,
|
| 762 |
+
"num_train_epochs": 20,
|
| 763 |
"total_flos": 6358548529152000.0,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c8ff86c8a019682990b3e68731bbdebe11c9e8cba636f73bf25cbdcdd1ec4db
|
| 3 |
+
size 3375
|