Training in progress, step 141
Browse files- model.safetensors +1 -1
- run-rukgjisn/checkpoint-141/config.json +22 -0
- run-rukgjisn/checkpoint-141/model.safetensors +3 -0
- run-rukgjisn/checkpoint-141/optimizer.pt +3 -0
- run-rukgjisn/checkpoint-141/rng_state.pth +3 -0
- run-rukgjisn/checkpoint-141/scheduler.pt +3 -0
- run-rukgjisn/checkpoint-141/trainer_state.json +745 -0
- run-rukgjisn/checkpoint-141/training_args.bin +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 605156676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d09b7e21715c345df914e334fa0c9663d9cebfebfebd86d03ea69315b85e9f
|
| 3 |
size 605156676
|
run-rukgjisn/checkpoint-141/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"model_type": "clip_text_model"
|
| 15 |
+
},
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"transformers_version": "4.42.0.dev0",
|
| 18 |
+
"vision_config": {
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"model_type": "clip_vision_model"
|
| 21 |
+
}
|
| 22 |
+
}
|
run-rukgjisn/checkpoint-141/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d09b7e21715c345df914e334fa0c9663d9cebfebfebd86d03ea69315b85e9f
|
| 3 |
+
size 605156676
|
run-rukgjisn/checkpoint-141/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8e1492c16e6617decac1692a61d9ebe0c3703083debe381bc3ba5220ecbdc5f
|
| 3 |
+
size 1210551612
|
run-rukgjisn/checkpoint-141/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e96fc8563484f6a8496903580e7bc7e8a2ce3b03a6219f8c18b38034a60c61e0
|
| 3 |
+
size 14244
|
run-rukgjisn/checkpoint-141/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2ff5b95c0d9fc9c1957bd86dceb741fb3264c2542974ebf2d568a92183b8c00
|
| 3 |
+
size 1064
|
run-rukgjisn/checkpoint-141/trainer_state.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 3,
|
| 6 |
+
"global_step": 141,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06382978723404255,
|
| 13 |
+
"grad_norm": 126.25067138671875,
|
| 14 |
+
"learning_rate": 2.7017280741018005e-06,
|
| 15 |
+
"loss": 2.0446,
|
| 16 |
+
"step": 3
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06382978723404255,
|
| 20 |
+
"eval_loss": 1.5570741891860962,
|
| 21 |
+
"eval_runtime": 138.2934,
|
| 22 |
+
"eval_samples_per_second": 2.169,
|
| 23 |
+
"eval_steps_per_second": 0.036,
|
| 24 |
+
"step": 3
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1276595744680851,
|
| 28 |
+
"grad_norm": 120.61219024658203,
|
| 29 |
+
"learning_rate": 2.642994855099588e-06,
|
| 30 |
+
"loss": 1.5291,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1276595744680851,
|
| 35 |
+
"eval_loss": 1.5480098724365234,
|
| 36 |
+
"eval_runtime": 55.4012,
|
| 37 |
+
"eval_samples_per_second": 5.415,
|
| 38 |
+
"eval_steps_per_second": 0.09,
|
| 39 |
+
"step": 6
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19148936170212766,
|
| 43 |
+
"grad_norm": 148.80548095703125,
|
| 44 |
+
"learning_rate": 2.5842616360973746e-06,
|
| 45 |
+
"loss": 1.5643,
|
| 46 |
+
"step": 9
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.19148936170212766,
|
| 50 |
+
"eval_loss": 1.493557095527649,
|
| 51 |
+
"eval_runtime": 63.0246,
|
| 52 |
+
"eval_samples_per_second": 4.76,
|
| 53 |
+
"eval_steps_per_second": 0.079,
|
| 54 |
+
"step": 9
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2553191489361702,
|
| 58 |
+
"grad_norm": 107.73375701904297,
|
| 59 |
+
"learning_rate": 2.5255284170951615e-06,
|
| 60 |
+
"loss": 1.4307,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.2553191489361702,
|
| 65 |
+
"eval_loss": 1.4424189329147339,
|
| 66 |
+
"eval_runtime": 75.4031,
|
| 67 |
+
"eval_samples_per_second": 3.979,
|
| 68 |
+
"eval_steps_per_second": 0.066,
|
| 69 |
+
"step": 12
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3191489361702128,
|
| 73 |
+
"grad_norm": 130.98121643066406,
|
| 74 |
+
"learning_rate": 2.4667951980929483e-06,
|
| 75 |
+
"loss": 1.6454,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.3191489361702128,
|
| 80 |
+
"eval_loss": 1.408605694770813,
|
| 81 |
+
"eval_runtime": 53.8295,
|
| 82 |
+
"eval_samples_per_second": 5.573,
|
| 83 |
+
"eval_steps_per_second": 0.093,
|
| 84 |
+
"step": 15
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.3829787234042553,
|
| 88 |
+
"grad_norm": 106.03084564208984,
|
| 89 |
+
"learning_rate": 2.4080619790907356e-06,
|
| 90 |
+
"loss": 1.3147,
|
| 91 |
+
"step": 18
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.3829787234042553,
|
| 95 |
+
"eval_loss": 1.3837209939956665,
|
| 96 |
+
"eval_runtime": 67.6789,
|
| 97 |
+
"eval_samples_per_second": 4.433,
|
| 98 |
+
"eval_steps_per_second": 0.074,
|
| 99 |
+
"step": 18
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.44680851063829785,
|
| 103 |
+
"grad_norm": 113.49714660644531,
|
| 104 |
+
"learning_rate": 2.3493287600885224e-06,
|
| 105 |
+
"loss": 1.2143,
|
| 106 |
+
"step": 21
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.44680851063829785,
|
| 110 |
+
"eval_loss": 1.3638520240783691,
|
| 111 |
+
"eval_runtime": 54.0491,
|
| 112 |
+
"eval_samples_per_second": 5.551,
|
| 113 |
+
"eval_steps_per_second": 0.093,
|
| 114 |
+
"step": 21
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5106382978723404,
|
| 118 |
+
"grad_norm": 113.10063934326172,
|
| 119 |
+
"learning_rate": 2.2905955410863092e-06,
|
| 120 |
+
"loss": 1.4135,
|
| 121 |
+
"step": 24
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5106382978723404,
|
| 125 |
+
"eval_loss": 1.3405903577804565,
|
| 126 |
+
"eval_runtime": 53.7778,
|
| 127 |
+
"eval_samples_per_second": 5.579,
|
| 128 |
+
"eval_steps_per_second": 0.093,
|
| 129 |
+
"step": 24
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.574468085106383,
|
| 133 |
+
"grad_norm": 140.38291931152344,
|
| 134 |
+
"learning_rate": 2.231862322084096e-06,
|
| 135 |
+
"loss": 1.5794,
|
| 136 |
+
"step": 27
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.574468085106383,
|
| 140 |
+
"eval_loss": 1.3204959630966187,
|
| 141 |
+
"eval_runtime": 53.6497,
|
| 142 |
+
"eval_samples_per_second": 5.592,
|
| 143 |
+
"eval_steps_per_second": 0.093,
|
| 144 |
+
"step": 27
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.6382978723404256,
|
| 148 |
+
"grad_norm": 76.08525085449219,
|
| 149 |
+
"learning_rate": 2.1731291030818833e-06,
|
| 150 |
+
"loss": 1.3112,
|
| 151 |
+
"step": 30
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6382978723404256,
|
| 155 |
+
"eval_loss": 1.3033435344696045,
|
| 156 |
+
"eval_runtime": 71.2383,
|
| 157 |
+
"eval_samples_per_second": 4.211,
|
| 158 |
+
"eval_steps_per_second": 0.07,
|
| 159 |
+
"step": 30
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7021276595744681,
|
| 163 |
+
"grad_norm": 92.6861801147461,
|
| 164 |
+
"learning_rate": 2.11439588407967e-06,
|
| 165 |
+
"loss": 1.5098,
|
| 166 |
+
"step": 33
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7021276595744681,
|
| 170 |
+
"eval_loss": 1.2886630296707153,
|
| 171 |
+
"eval_runtime": 67.4449,
|
| 172 |
+
"eval_samples_per_second": 4.448,
|
| 173 |
+
"eval_steps_per_second": 0.074,
|
| 174 |
+
"step": 33
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.7659574468085106,
|
| 178 |
+
"grad_norm": 109.13264465332031,
|
| 179 |
+
"learning_rate": 2.055662665077457e-06,
|
| 180 |
+
"loss": 1.6407,
|
| 181 |
+
"step": 36
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7659574468085106,
|
| 185 |
+
"eval_loss": 1.273186445236206,
|
| 186 |
+
"eval_runtime": 54.8832,
|
| 187 |
+
"eval_samples_per_second": 5.466,
|
| 188 |
+
"eval_steps_per_second": 0.091,
|
| 189 |
+
"step": 36
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.8297872340425532,
|
| 193 |
+
"grad_norm": 78.30274200439453,
|
| 194 |
+
"learning_rate": 1.9969294460752442e-06,
|
| 195 |
+
"loss": 1.4043,
|
| 196 |
+
"step": 39
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8297872340425532,
|
| 200 |
+
"eval_loss": 1.2596654891967773,
|
| 201 |
+
"eval_runtime": 54.429,
|
| 202 |
+
"eval_samples_per_second": 5.512,
|
| 203 |
+
"eval_steps_per_second": 0.092,
|
| 204 |
+
"step": 39
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.8936170212765957,
|
| 208 |
+
"grad_norm": 93.06748962402344,
|
| 209 |
+
"learning_rate": 1.938196227073031e-06,
|
| 210 |
+
"loss": 1.3401,
|
| 211 |
+
"step": 42
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.8936170212765957,
|
| 215 |
+
"eval_loss": 1.2511677742004395,
|
| 216 |
+
"eval_runtime": 54.4103,
|
| 217 |
+
"eval_samples_per_second": 5.514,
|
| 218 |
+
"eval_steps_per_second": 0.092,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9574468085106383,
|
| 223 |
+
"grad_norm": 84.16166687011719,
|
| 224 |
+
"learning_rate": 1.8794630080708177e-06,
|
| 225 |
+
"loss": 1.2157,
|
| 226 |
+
"step": 45
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9574468085106383,
|
| 230 |
+
"eval_loss": 1.2443844079971313,
|
| 231 |
+
"eval_runtime": 54.268,
|
| 232 |
+
"eval_samples_per_second": 5.528,
|
| 233 |
+
"eval_steps_per_second": 0.092,
|
| 234 |
+
"step": 45
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0212765957446808,
|
| 238 |
+
"grad_norm": 55.88615417480469,
|
| 239 |
+
"learning_rate": 1.8207297890686047e-06,
|
| 240 |
+
"loss": 1.1511,
|
| 241 |
+
"step": 48
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0212765957446808,
|
| 245 |
+
"eval_loss": 1.231595516204834,
|
| 246 |
+
"eval_runtime": 54.7796,
|
| 247 |
+
"eval_samples_per_second": 5.476,
|
| 248 |
+
"eval_steps_per_second": 0.091,
|
| 249 |
+
"step": 48
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0851063829787233,
|
| 253 |
+
"grad_norm": 46.52244567871094,
|
| 254 |
+
"learning_rate": 1.7619965700663918e-06,
|
| 255 |
+
"loss": 0.8315,
|
| 256 |
+
"step": 51
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0851063829787233,
|
| 260 |
+
"eval_loss": 1.2207295894622803,
|
| 261 |
+
"eval_runtime": 53.8738,
|
| 262 |
+
"eval_samples_per_second": 5.569,
|
| 263 |
+
"eval_steps_per_second": 0.093,
|
| 264 |
+
"step": 51
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.148936170212766,
|
| 268 |
+
"grad_norm": 44.749393463134766,
|
| 269 |
+
"learning_rate": 1.7032633510641786e-06,
|
| 270 |
+
"loss": 0.6485,
|
| 271 |
+
"step": 54
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.148936170212766,
|
| 275 |
+
"eval_loss": 1.209995985031128,
|
| 276 |
+
"eval_runtime": 78.7141,
|
| 277 |
+
"eval_samples_per_second": 3.811,
|
| 278 |
+
"eval_steps_per_second": 0.064,
|
| 279 |
+
"step": 54
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.2127659574468086,
|
| 283 |
+
"grad_norm": 63.92289733886719,
|
| 284 |
+
"learning_rate": 1.6445301320619655e-06,
|
| 285 |
+
"loss": 0.8721,
|
| 286 |
+
"step": 57
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.2127659574468086,
|
| 290 |
+
"eval_loss": 1.2013087272644043,
|
| 291 |
+
"eval_runtime": 53.3669,
|
| 292 |
+
"eval_samples_per_second": 5.621,
|
| 293 |
+
"eval_steps_per_second": 0.094,
|
| 294 |
+
"step": 57
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.2765957446808511,
|
| 298 |
+
"grad_norm": 45.4834098815918,
|
| 299 |
+
"learning_rate": 1.5857969130597527e-06,
|
| 300 |
+
"loss": 0.7515,
|
| 301 |
+
"step": 60
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.2765957446808511,
|
| 305 |
+
"eval_loss": 1.1964448690414429,
|
| 306 |
+
"eval_runtime": 53.8155,
|
| 307 |
+
"eval_samples_per_second": 5.575,
|
| 308 |
+
"eval_steps_per_second": 0.093,
|
| 309 |
+
"step": 60
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3404255319148937,
|
| 313 |
+
"grad_norm": 46.8050422668457,
|
| 314 |
+
"learning_rate": 1.5270636940575396e-06,
|
| 315 |
+
"loss": 0.5828,
|
| 316 |
+
"step": 63
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.3404255319148937,
|
| 320 |
+
"eval_loss": 1.195375919342041,
|
| 321 |
+
"eval_runtime": 53.8711,
|
| 322 |
+
"eval_samples_per_second": 5.569,
|
| 323 |
+
"eval_steps_per_second": 0.093,
|
| 324 |
+
"step": 63
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.4042553191489362,
|
| 328 |
+
"grad_norm": 66.9081039428711,
|
| 329 |
+
"learning_rate": 1.4683304750553264e-06,
|
| 330 |
+
"loss": 0.7587,
|
| 331 |
+
"step": 66
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.4042553191489362,
|
| 335 |
+
"eval_loss": 1.1937648057937622,
|
| 336 |
+
"eval_runtime": 54.3286,
|
| 337 |
+
"eval_samples_per_second": 5.522,
|
| 338 |
+
"eval_steps_per_second": 0.092,
|
| 339 |
+
"step": 66
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4680851063829787,
|
| 343 |
+
"grad_norm": 66.40003204345703,
|
| 344 |
+
"learning_rate": 1.4095972560531132e-06,
|
| 345 |
+
"loss": 0.8638,
|
| 346 |
+
"step": 69
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4680851063829787,
|
| 350 |
+
"eval_loss": 1.1902137994766235,
|
| 351 |
+
"eval_runtime": 54.7582,
|
| 352 |
+
"eval_samples_per_second": 5.479,
|
| 353 |
+
"eval_steps_per_second": 0.091,
|
| 354 |
+
"step": 69
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.5319148936170213,
|
| 358 |
+
"grad_norm": 62.0701789855957,
|
| 359 |
+
"learning_rate": 1.3508640370509003e-06,
|
| 360 |
+
"loss": 0.757,
|
| 361 |
+
"step": 72
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5319148936170213,
|
| 365 |
+
"eval_loss": 1.1826313734054565,
|
| 366 |
+
"eval_runtime": 54.1709,
|
| 367 |
+
"eval_samples_per_second": 5.538,
|
| 368 |
+
"eval_steps_per_second": 0.092,
|
| 369 |
+
"step": 72
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.5957446808510638,
|
| 373 |
+
"grad_norm": 75.45089721679688,
|
| 374 |
+
"learning_rate": 1.2921308180486873e-06,
|
| 375 |
+
"loss": 0.9248,
|
| 376 |
+
"step": 75
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.5957446808510638,
|
| 380 |
+
"eval_loss": 1.174964189529419,
|
| 381 |
+
"eval_runtime": 54.2646,
|
| 382 |
+
"eval_samples_per_second": 5.528,
|
| 383 |
+
"eval_steps_per_second": 0.092,
|
| 384 |
+
"step": 75
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.6595744680851063,
|
| 388 |
+
"grad_norm": 55.88802719116211,
|
| 389 |
+
"learning_rate": 1.2333975990464741e-06,
|
| 390 |
+
"loss": 0.7642,
|
| 391 |
+
"step": 78
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.6595744680851063,
|
| 395 |
+
"eval_loss": 1.1686428785324097,
|
| 396 |
+
"eval_runtime": 64.2026,
|
| 397 |
+
"eval_samples_per_second": 4.673,
|
| 398 |
+
"eval_steps_per_second": 0.078,
|
| 399 |
+
"step": 78
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.7234042553191489,
|
| 403 |
+
"grad_norm": 65.16743469238281,
|
| 404 |
+
"learning_rate": 1.1746643800442612e-06,
|
| 405 |
+
"loss": 0.6538,
|
| 406 |
+
"step": 81
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.7234042553191489,
|
| 410 |
+
"eval_loss": 1.162994623184204,
|
| 411 |
+
"eval_runtime": 55.9418,
|
| 412 |
+
"eval_samples_per_second": 5.363,
|
| 413 |
+
"eval_steps_per_second": 0.089,
|
| 414 |
+
"step": 81
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.7872340425531914,
|
| 418 |
+
"grad_norm": 62.544212341308594,
|
| 419 |
+
"learning_rate": 1.115931161042048e-06,
|
| 420 |
+
"loss": 0.7696,
|
| 421 |
+
"step": 84
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.7872340425531914,
|
| 425 |
+
"eval_loss": 1.1596062183380127,
|
| 426 |
+
"eval_runtime": 54.4231,
|
| 427 |
+
"eval_samples_per_second": 5.512,
|
| 428 |
+
"eval_steps_per_second": 0.092,
|
| 429 |
+
"step": 84
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.851063829787234,
|
| 433 |
+
"grad_norm": 72.0561752319336,
|
| 434 |
+
"learning_rate": 1.057197942039835e-06,
|
| 435 |
+
"loss": 0.803,
|
| 436 |
+
"step": 87
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.851063829787234,
|
| 440 |
+
"eval_loss": 1.1562731266021729,
|
| 441 |
+
"eval_runtime": 55.0497,
|
| 442 |
+
"eval_samples_per_second": 5.45,
|
| 443 |
+
"eval_steps_per_second": 0.091,
|
| 444 |
+
"step": 87
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9148936170212765,
|
| 448 |
+
"grad_norm": 55.98563766479492,
|
| 449 |
+
"learning_rate": 9.984647230376221e-07,
|
| 450 |
+
"loss": 0.648,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9148936170212765,
|
| 455 |
+
"eval_loss": 1.1566147804260254,
|
| 456 |
+
"eval_runtime": 55.0097,
|
| 457 |
+
"eval_samples_per_second": 5.454,
|
| 458 |
+
"eval_steps_per_second": 0.091,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.978723404255319,
|
| 463 |
+
"grad_norm": 54.97642517089844,
|
| 464 |
+
"learning_rate": 9.397315040354089e-07,
|
| 465 |
+
"loss": 0.7102,
|
| 466 |
+
"step": 93
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.978723404255319,
|
| 470 |
+
"eval_loss": 1.1567518711090088,
|
| 471 |
+
"eval_runtime": 55.4659,
|
| 472 |
+
"eval_samples_per_second": 5.409,
|
| 473 |
+
"eval_steps_per_second": 0.09,
|
| 474 |
+
"step": 93
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0425531914893615,
|
| 478 |
+
"grad_norm": 62.32664489746094,
|
| 479 |
+
"learning_rate": 8.809982850331959e-07,
|
| 480 |
+
"loss": 0.7291,
|
| 481 |
+
"step": 96
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.0425531914893615,
|
| 485 |
+
"eval_loss": 1.155635952949524,
|
| 486 |
+
"eval_runtime": 58.8091,
|
| 487 |
+
"eval_samples_per_second": 5.101,
|
| 488 |
+
"eval_steps_per_second": 0.085,
|
| 489 |
+
"step": 96
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.106382978723404,
|
| 493 |
+
"grad_norm": 38.61061096191406,
|
| 494 |
+
"learning_rate": 8.222650660309827e-07,
|
| 495 |
+
"loss": 0.5435,
|
| 496 |
+
"step": 99
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.106382978723404,
|
| 500 |
+
"eval_loss": 1.1566288471221924,
|
| 501 |
+
"eval_runtime": 61.3747,
|
| 502 |
+
"eval_samples_per_second": 4.888,
|
| 503 |
+
"eval_steps_per_second": 0.081,
|
| 504 |
+
"step": 99
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.1702127659574466,
|
| 508 |
+
"grad_norm": 37.246219635009766,
|
| 509 |
+
"learning_rate": 7.635318470287698e-07,
|
| 510 |
+
"loss": 0.4237,
|
| 511 |
+
"step": 102
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.1702127659574466,
|
| 515 |
+
"eval_loss": 1.1587642431259155,
|
| 516 |
+
"eval_runtime": 54.2257,
|
| 517 |
+
"eval_samples_per_second": 5.532,
|
| 518 |
+
"eval_steps_per_second": 0.092,
|
| 519 |
+
"step": 102
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.2340425531914896,
|
| 523 |
+
"grad_norm": 53.6576042175293,
|
| 524 |
+
"learning_rate": 7.047986280265566e-07,
|
| 525 |
+
"loss": 0.599,
|
| 526 |
+
"step": 105
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.2340425531914896,
|
| 530 |
+
"eval_loss": 1.1605359315872192,
|
| 531 |
+
"eval_runtime": 74.2548,
|
| 532 |
+
"eval_samples_per_second": 4.04,
|
| 533 |
+
"eval_steps_per_second": 0.067,
|
| 534 |
+
"step": 105
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.297872340425532,
|
| 538 |
+
"grad_norm": 53.27869415283203,
|
| 539 |
+
"learning_rate": 6.460654090243437e-07,
|
| 540 |
+
"loss": 0.5356,
|
| 541 |
+
"step": 108
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.297872340425532,
|
| 545 |
+
"eval_loss": 1.1615859270095825,
|
| 546 |
+
"eval_runtime": 54.2089,
|
| 547 |
+
"eval_samples_per_second": 5.534,
|
| 548 |
+
"eval_steps_per_second": 0.092,
|
| 549 |
+
"step": 108
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.3617021276595747,
|
| 553 |
+
"grad_norm": 53.355735778808594,
|
| 554 |
+
"learning_rate": 5.873321900221306e-07,
|
| 555 |
+
"loss": 0.4193,
|
| 556 |
+
"step": 111
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.3617021276595747,
|
| 560 |
+
"eval_loss": 1.162276029586792,
|
| 561 |
+
"eval_runtime": 54.4971,
|
| 562 |
+
"eval_samples_per_second": 5.505,
|
| 563 |
+
"eval_steps_per_second": 0.092,
|
| 564 |
+
"step": 111
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.425531914893617,
|
| 568 |
+
"grad_norm": 49.23762512207031,
|
| 569 |
+
"learning_rate": 5.285989710199175e-07,
|
| 570 |
+
"loss": 0.4437,
|
| 571 |
+
"step": 114
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.425531914893617,
|
| 575 |
+
"eval_loss": 1.1603819131851196,
|
| 576 |
+
"eval_runtime": 54.4206,
|
| 577 |
+
"eval_samples_per_second": 5.513,
|
| 578 |
+
"eval_steps_per_second": 0.092,
|
| 579 |
+
"step": 114
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.4893617021276597,
|
| 583 |
+
"grad_norm": 53.271141052246094,
|
| 584 |
+
"learning_rate": 4.698657520177044e-07,
|
| 585 |
+
"loss": 0.4134,
|
| 586 |
+
"step": 117
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.4893617021276597,
|
| 590 |
+
"eval_loss": 1.1590569019317627,
|
| 591 |
+
"eval_runtime": 54.4573,
|
| 592 |
+
"eval_samples_per_second": 5.509,
|
| 593 |
+
"eval_steps_per_second": 0.092,
|
| 594 |
+
"step": 117
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.5531914893617023,
|
| 598 |
+
"grad_norm": 49.70021057128906,
|
| 599 |
+
"learning_rate": 4.1113253301549137e-07,
|
| 600 |
+
"loss": 0.5297,
|
| 601 |
+
"step": 120
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.5531914893617023,
|
| 605 |
+
"eval_loss": 1.1584316492080688,
|
| 606 |
+
"eval_runtime": 72.8487,
|
| 607 |
+
"eval_samples_per_second": 4.118,
|
| 608 |
+
"eval_steps_per_second": 0.069,
|
| 609 |
+
"step": 120
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.617021276595745,
|
| 613 |
+
"grad_norm": 85.43531036376953,
|
| 614 |
+
"learning_rate": 3.523993140132783e-07,
|
| 615 |
+
"loss": 0.5691,
|
| 616 |
+
"step": 123
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.617021276595745,
|
| 620 |
+
"eval_loss": 1.157990574836731,
|
| 621 |
+
"eval_runtime": 54.3078,
|
| 622 |
+
"eval_samples_per_second": 5.524,
|
| 623 |
+
"eval_steps_per_second": 0.092,
|
| 624 |
+
"step": 123
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.6808510638297873,
|
| 628 |
+
"grad_norm": 37.16761016845703,
|
| 629 |
+
"learning_rate": 2.936660950110653e-07,
|
| 630 |
+
"loss": 0.3697,
|
| 631 |
+
"step": 126
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.6808510638297873,
|
| 635 |
+
"eval_loss": 1.158142328262329,
|
| 636 |
+
"eval_runtime": 59.3308,
|
| 637 |
+
"eval_samples_per_second": 5.056,
|
| 638 |
+
"eval_steps_per_second": 0.084,
|
| 639 |
+
"step": 126
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.74468085106383,
|
| 643 |
+
"grad_norm": 53.20654296875,
|
| 644 |
+
"learning_rate": 2.349328760088522e-07,
|
| 645 |
+
"loss": 0.4085,
|
| 646 |
+
"step": 129
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.74468085106383,
|
| 650 |
+
"eval_loss": 1.1589455604553223,
|
| 651 |
+
"eval_runtime": 53.9966,
|
| 652 |
+
"eval_samples_per_second": 5.556,
|
| 653 |
+
"eval_steps_per_second": 0.093,
|
| 654 |
+
"step": 129
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.8085106382978724,
|
| 658 |
+
"grad_norm": 52.14693832397461,
|
| 659 |
+
"learning_rate": 1.7619965700663915e-07,
|
| 660 |
+
"loss": 0.4542,
|
| 661 |
+
"step": 132
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.8085106382978724,
|
| 665 |
+
"eval_loss": 1.1593271493911743,
|
| 666 |
+
"eval_runtime": 55.1703,
|
| 667 |
+
"eval_samples_per_second": 5.438,
|
| 668 |
+
"eval_steps_per_second": 0.091,
|
| 669 |
+
"step": 132
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.872340425531915,
|
| 673 |
+
"grad_norm": 42.75836944580078,
|
| 674 |
+
"learning_rate": 1.174664380044261e-07,
|
| 675 |
+
"loss": 0.4124,
|
| 676 |
+
"step": 135
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.872340425531915,
|
| 680 |
+
"eval_loss": 1.1595427989959717,
|
| 681 |
+
"eval_runtime": 54.8115,
|
| 682 |
+
"eval_samples_per_second": 5.473,
|
| 683 |
+
"eval_steps_per_second": 0.091,
|
| 684 |
+
"step": 135
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.9361702127659575,
|
| 688 |
+
"grad_norm": 44.63527297973633,
|
| 689 |
+
"learning_rate": 5.873321900221305e-08,
|
| 690 |
+
"loss": 0.5137,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.9361702127659575,
|
| 695 |
+
"eval_loss": 1.1596213579177856,
|
| 696 |
+
"eval_runtime": 54.0814,
|
| 697 |
+
"eval_samples_per_second": 5.547,
|
| 698 |
+
"eval_steps_per_second": 0.092,
|
| 699 |
+
"step": 138
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.0,
|
| 703 |
+
"grad_norm": 56.000244140625,
|
| 704 |
+
"learning_rate": 0.0,
|
| 705 |
+
"loss": 0.4429,
|
| 706 |
+
"step": 141
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.0,
|
| 710 |
+
"eval_loss": 1.1596343517303467,
|
| 711 |
+
"eval_runtime": 58.7466,
|
| 712 |
+
"eval_samples_per_second": 5.107,
|
| 713 |
+
"eval_steps_per_second": 0.085,
|
| 714 |
+
"step": 141
|
| 715 |
+
}
|
| 716 |
+
],
|
| 717 |
+
"logging_steps": 3,
|
| 718 |
+
"max_steps": 141,
|
| 719 |
+
"num_input_tokens_seen": 0,
|
| 720 |
+
"num_train_epochs": 3,
|
| 721 |
+
"save_steps": 500,
|
| 722 |
+
"stateful_callbacks": {
|
| 723 |
+
"TrainerControl": {
|
| 724 |
+
"args": {
|
| 725 |
+
"should_epoch_stop": false,
|
| 726 |
+
"should_evaluate": false,
|
| 727 |
+
"should_log": false,
|
| 728 |
+
"should_save": true,
|
| 729 |
+
"should_training_stop": true
|
| 730 |
+
},
|
| 731 |
+
"attributes": {}
|
| 732 |
+
}
|
| 733 |
+
},
|
| 734 |
+
"total_flos": 523328480700102.0,
|
| 735 |
+
"train_batch_size": 64,
|
| 736 |
+
"trial_name": null,
|
| 737 |
+
"trial_params": {
|
| 738 |
+
"_wandb": {},
|
| 739 |
+
"assignments": {},
|
| 740 |
+
"decay": 0.01,
|
| 741 |
+
"learning_rate": 2.7604612931040137e-06,
|
| 742 |
+
"metric": "eval/loss",
|
| 743 |
+
"per_device_train_batch_size": 64
|
| 744 |
+
}
|
| 745 |
+
}
|
run-rukgjisn/checkpoint-141/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f32e56a92fc888c2246e5b72e7d93d10f0ea6484a0289837bffd6e64aaa0db1c
|
| 3 |
+
size 5112
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f32e56a92fc888c2246e5b72e7d93d10f0ea6484a0289837bffd6e64aaa0db1c
|
| 3 |
size 5112
|