Training in progress, step 110
Browse files- model.safetensors +1 -1
- run-wgja68lo/checkpoint-110/config.json +22 -0
- run-wgja68lo/checkpoint-110/model.safetensors +3 -0
- run-wgja68lo/checkpoint-110/optimizer.pt +3 -0
- run-wgja68lo/checkpoint-110/rng_state.pth +3 -0
- run-wgja68lo/checkpoint-110/scheduler.pt +3 -0
- run-wgja68lo/checkpoint-110/trainer_state.json +865 -0
- run-wgja68lo/checkpoint-110/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 sha256:352172f076d6a58ebf2fc85e11b1cbc041ccf3a96a3ea3e2f8b1e6a9c0fcf049
|
| 3 |
size 605156676
|
run-wgja68lo/checkpoint-110/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-wgja68lo/checkpoint-110/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:352172f076d6a58ebf2fc85e11b1cbc041ccf3a96a3ea3e2f8b1e6a9c0fcf049
|
| 3 |
+
size 605156676
|
run-wgja68lo/checkpoint-110/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74bf7e861a9d3432e4f142b660c2df80ad4249de87e94e287f3c471e652d336a
|
| 3 |
+
size 1210551612
|
run-wgja68lo/checkpoint-110/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16629df2819a8d44b43da4938948e4713f44200e43c923a476715285313928f0
|
| 3 |
+
size 14244
|
run-wgja68lo/checkpoint-110/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d663d07e1f9020b5d7720335f45763a001928feb06edd02fcff9e48232361a86
|
| 3 |
+
size 1064
|
run-wgja68lo/checkpoint-110/trainer_state.json
ADDED
|
@@ -0,0 +1,865 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 2,
|
| 6 |
+
"global_step": 110,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03636363636363636,
|
| 13 |
+
"grad_norm": 156.3038787841797,
|
| 14 |
+
"learning_rate": 0.0002480103771818548,
|
| 15 |
+
"loss": 3.8254,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03636363636363636,
|
| 20 |
+
"eval_loss": 4.441679000854492,
|
| 21 |
+
"eval_runtime": 138.5108,
|
| 22 |
+
"eval_samples_per_second": 2.527,
|
| 23 |
+
"eval_steps_per_second": 0.043,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07272727272727272,
|
| 28 |
+
"grad_norm": 121.79210662841797,
|
| 29 |
+
"learning_rate": 0.00024341759241922788,
|
| 30 |
+
"loss": 5.6376,
|
| 31 |
+
"step": 4
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07272727272727272,
|
| 35 |
+
"eval_loss": 6.213077545166016,
|
| 36 |
+
"eval_runtime": 169.0449,
|
| 37 |
+
"eval_samples_per_second": 2.07,
|
| 38 |
+
"eval_steps_per_second": 0.035,
|
| 39 |
+
"step": 4
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.10909090909090909,
|
| 43 |
+
"grad_norm": 3.2695116996765137,
|
| 44 |
+
"learning_rate": 0.00023882480765660094,
|
| 45 |
+
"loss": 5.484,
|
| 46 |
+
"step": 6
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.10909090909090909,
|
| 50 |
+
"eval_loss": 4.189974308013916,
|
| 51 |
+
"eval_runtime": 150.2603,
|
| 52 |
+
"eval_samples_per_second": 2.329,
|
| 53 |
+
"eval_steps_per_second": 0.04,
|
| 54 |
+
"step": 6
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.14545454545454545,
|
| 58 |
+
"grad_norm": 0.20998883247375488,
|
| 59 |
+
"learning_rate": 0.00023423202289397398,
|
| 60 |
+
"loss": 4.212,
|
| 61 |
+
"step": 8
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.14545454545454545,
|
| 65 |
+
"eval_loss": 4.095343112945557,
|
| 66 |
+
"eval_runtime": 108.8466,
|
| 67 |
+
"eval_samples_per_second": 3.216,
|
| 68 |
+
"eval_steps_per_second": 0.055,
|
| 69 |
+
"step": 8
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.18181818181818182,
|
| 73 |
+
"grad_norm": 0.05422870069742203,
|
| 74 |
+
"learning_rate": 0.00022963923813134704,
|
| 75 |
+
"loss": 4.16,
|
| 76 |
+
"step": 10
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.18181818181818182,
|
| 80 |
+
"eval_loss": 4.094566822052002,
|
| 81 |
+
"eval_runtime": 117.133,
|
| 82 |
+
"eval_samples_per_second": 2.988,
|
| 83 |
+
"eval_steps_per_second": 0.051,
|
| 84 |
+
"step": 10
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.21818181818181817,
|
| 88 |
+
"grad_norm": 0.043678443878889084,
|
| 89 |
+
"learning_rate": 0.0002250464533687201,
|
| 90 |
+
"loss": 4.1595,
|
| 91 |
+
"step": 12
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.21818181818181817,
|
| 95 |
+
"eval_loss": 4.094362258911133,
|
| 96 |
+
"eval_runtime": 115.9567,
|
| 97 |
+
"eval_samples_per_second": 3.018,
|
| 98 |
+
"eval_steps_per_second": 0.052,
|
| 99 |
+
"step": 12
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.2545454545454545,
|
| 103 |
+
"grad_norm": 0.024278217926621437,
|
| 104 |
+
"learning_rate": 0.00022045366860609316,
|
| 105 |
+
"loss": 4.1593,
|
| 106 |
+
"step": 14
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.2545454545454545,
|
| 110 |
+
"eval_loss": 4.09407377243042,
|
| 111 |
+
"eval_runtime": 108.3601,
|
| 112 |
+
"eval_samples_per_second": 3.23,
|
| 113 |
+
"eval_steps_per_second": 0.055,
|
| 114 |
+
"step": 14
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2909090909090909,
|
| 118 |
+
"grad_norm": 0.00787164457142353,
|
| 119 |
+
"learning_rate": 0.00021586088384346623,
|
| 120 |
+
"loss": 4.159,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2909090909090909,
|
| 125 |
+
"eval_loss": 4.094001770019531,
|
| 126 |
+
"eval_runtime": 108.9106,
|
| 127 |
+
"eval_samples_per_second": 3.214,
|
| 128 |
+
"eval_steps_per_second": 0.055,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.32727272727272727,
|
| 133 |
+
"grad_norm": 0.008814062923192978,
|
| 134 |
+
"learning_rate": 0.0002112680990808393,
|
| 135 |
+
"loss": 4.159,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.32727272727272727,
|
| 140 |
+
"eval_loss": 4.094032287597656,
|
| 141 |
+
"eval_runtime": 108.5561,
|
| 142 |
+
"eval_samples_per_second": 3.224,
|
| 143 |
+
"eval_steps_per_second": 0.055,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.36363636363636365,
|
| 148 |
+
"grad_norm": 0.011641773395240307,
|
| 149 |
+
"learning_rate": 0.00020667531431821235,
|
| 150 |
+
"loss": 4.159,
|
| 151 |
+
"step": 20
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.36363636363636365,
|
| 155 |
+
"eval_loss": 4.094035625457764,
|
| 156 |
+
"eval_runtime": 109.9627,
|
| 157 |
+
"eval_samples_per_second": 3.183,
|
| 158 |
+
"eval_steps_per_second": 0.055,
|
| 159 |
+
"step": 20
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.4,
|
| 163 |
+
"grad_norm": 0.010468115098774433,
|
| 164 |
+
"learning_rate": 0.0002020825295555854,
|
| 165 |
+
"loss": 4.159,
|
| 166 |
+
"step": 22
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.4,
|
| 170 |
+
"eval_loss": 4.093992233276367,
|
| 171 |
+
"eval_runtime": 109.2553,
|
| 172 |
+
"eval_samples_per_second": 3.204,
|
| 173 |
+
"eval_steps_per_second": 0.055,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.43636363636363634,
|
| 178 |
+
"grad_norm": 0.004853196442127228,
|
| 179 |
+
"learning_rate": 0.00019748974479295847,
|
| 180 |
+
"loss": 4.1589,
|
| 181 |
+
"step": 24
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.43636363636363634,
|
| 185 |
+
"eval_loss": 4.093957901000977,
|
| 186 |
+
"eval_runtime": 110.1754,
|
| 187 |
+
"eval_samples_per_second": 3.177,
|
| 188 |
+
"eval_steps_per_second": 0.054,
|
| 189 |
+
"step": 24
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4727272727272727,
|
| 193 |
+
"grad_norm": 0.003641755087301135,
|
| 194 |
+
"learning_rate": 0.00019289696003033154,
|
| 195 |
+
"loss": 4.1589,
|
| 196 |
+
"step": 26
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.4727272727272727,
|
| 200 |
+
"eval_loss": 4.093954563140869,
|
| 201 |
+
"eval_runtime": 109.1144,
|
| 202 |
+
"eval_samples_per_second": 3.208,
|
| 203 |
+
"eval_steps_per_second": 0.055,
|
| 204 |
+
"step": 26
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.509090909090909,
|
| 208 |
+
"grad_norm": 0.004993860609829426,
|
| 209 |
+
"learning_rate": 0.0001883041752677046,
|
| 210 |
+
"loss": 4.1589,
|
| 211 |
+
"step": 28
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.509090909090909,
|
| 215 |
+
"eval_loss": 4.093963146209717,
|
| 216 |
+
"eval_runtime": 201.6876,
|
| 217 |
+
"eval_samples_per_second": 1.735,
|
| 218 |
+
"eval_steps_per_second": 0.03,
|
| 219 |
+
"step": 28
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5454545454545454,
|
| 223 |
+
"grad_norm": 0.005196776241064072,
|
| 224 |
+
"learning_rate": 0.00018371139050507766,
|
| 225 |
+
"loss": 4.1589,
|
| 226 |
+
"step": 30
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5454545454545454,
|
| 230 |
+
"eval_loss": 4.093966007232666,
|
| 231 |
+
"eval_runtime": 118.6265,
|
| 232 |
+
"eval_samples_per_second": 2.95,
|
| 233 |
+
"eval_steps_per_second": 0.051,
|
| 234 |
+
"step": 30
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5818181818181818,
|
| 238 |
+
"grad_norm": 0.0044463989324867725,
|
| 239 |
+
"learning_rate": 0.0001791186057424507,
|
| 240 |
+
"loss": 4.1589,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5818181818181818,
|
| 245 |
+
"eval_loss": 4.093958377838135,
|
| 246 |
+
"eval_runtime": 115.5925,
|
| 247 |
+
"eval_samples_per_second": 3.028,
|
| 248 |
+
"eval_steps_per_second": 0.052,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.6181818181818182,
|
| 253 |
+
"grad_norm": 0.0034679854288697243,
|
| 254 |
+
"learning_rate": 0.00017452582097982376,
|
| 255 |
+
"loss": 4.1589,
|
| 256 |
+
"step": 34
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.6181818181818182,
|
| 260 |
+
"eval_loss": 4.093946933746338,
|
| 261 |
+
"eval_runtime": 146.8875,
|
| 262 |
+
"eval_samples_per_second": 2.383,
|
| 263 |
+
"eval_steps_per_second": 0.041,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6545454545454545,
|
| 268 |
+
"grad_norm": 0.002400787780061364,
|
| 269 |
+
"learning_rate": 0.00016993303621719682,
|
| 270 |
+
"loss": 4.1589,
|
| 271 |
+
"step": 36
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.6545454545454545,
|
| 275 |
+
"eval_loss": 4.0939412117004395,
|
| 276 |
+
"eval_runtime": 149.1826,
|
| 277 |
+
"eval_samples_per_second": 2.346,
|
| 278 |
+
"eval_steps_per_second": 0.04,
|
| 279 |
+
"step": 36
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.6909090909090909,
|
| 283 |
+
"grad_norm": 0.001346707926131785,
|
| 284 |
+
"learning_rate": 0.00016534025145456988,
|
| 285 |
+
"loss": 4.1589,
|
| 286 |
+
"step": 38
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.6909090909090909,
|
| 290 |
+
"eval_loss": 4.093942642211914,
|
| 291 |
+
"eval_runtime": 107.8083,
|
| 292 |
+
"eval_samples_per_second": 3.247,
|
| 293 |
+
"eval_steps_per_second": 0.056,
|
| 294 |
+
"step": 38
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.7272727272727273,
|
| 298 |
+
"grad_norm": 0.002782245399430394,
|
| 299 |
+
"learning_rate": 0.00016074746669194294,
|
| 300 |
+
"loss": 4.1589,
|
| 301 |
+
"step": 40
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.7272727272727273,
|
| 305 |
+
"eval_loss": 4.093945503234863,
|
| 306 |
+
"eval_runtime": 154.0308,
|
| 307 |
+
"eval_samples_per_second": 2.272,
|
| 308 |
+
"eval_steps_per_second": 0.039,
|
| 309 |
+
"step": 40
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.7636363636363637,
|
| 313 |
+
"grad_norm": 0.00260904454626143,
|
| 314 |
+
"learning_rate": 0.000156154681929316,
|
| 315 |
+
"loss": 4.1589,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.7636363636363637,
|
| 320 |
+
"eval_loss": 4.093945503234863,
|
| 321 |
+
"eval_runtime": 112.4159,
|
| 322 |
+
"eval_samples_per_second": 3.113,
|
| 323 |
+
"eval_steps_per_second": 0.053,
|
| 324 |
+
"step": 42
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8,
|
| 328 |
+
"grad_norm": 0.002523690229281783,
|
| 329 |
+
"learning_rate": 0.00015156189716668904,
|
| 330 |
+
"loss": 4.1589,
|
| 331 |
+
"step": 44
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8,
|
| 335 |
+
"eval_loss": 4.093942642211914,
|
| 336 |
+
"eval_runtime": 124.943,
|
| 337 |
+
"eval_samples_per_second": 2.801,
|
| 338 |
+
"eval_steps_per_second": 0.048,
|
| 339 |
+
"step": 44
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8363636363636363,
|
| 343 |
+
"grad_norm": 0.002061552833765745,
|
| 344 |
+
"learning_rate": 0.0001469691124040621,
|
| 345 |
+
"loss": 4.1589,
|
| 346 |
+
"step": 46
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8363636363636363,
|
| 350 |
+
"eval_loss": 4.093940258026123,
|
| 351 |
+
"eval_runtime": 108.0115,
|
| 352 |
+
"eval_samples_per_second": 3.24,
|
| 353 |
+
"eval_steps_per_second": 0.056,
|
| 354 |
+
"step": 46
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.8727272727272727,
|
| 358 |
+
"grad_norm": 0.0015735819470137358,
|
| 359 |
+
"learning_rate": 0.00014237632764143516,
|
| 360 |
+
"loss": 4.1589,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.8727272727272727,
|
| 365 |
+
"eval_loss": 4.093937873840332,
|
| 366 |
+
"eval_runtime": 115.9852,
|
| 367 |
+
"eval_samples_per_second": 3.018,
|
| 368 |
+
"eval_steps_per_second": 0.052,
|
| 369 |
+
"step": 48
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.9090909090909091,
|
| 373 |
+
"grad_norm": 0.001207723980769515,
|
| 374 |
+
"learning_rate": 0.00013778354287880822,
|
| 375 |
+
"loss": 4.1589,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.9090909090909091,
|
| 380 |
+
"eval_loss": 4.093936443328857,
|
| 381 |
+
"eval_runtime": 155.9244,
|
| 382 |
+
"eval_samples_per_second": 2.245,
|
| 383 |
+
"eval_steps_per_second": 0.038,
|
| 384 |
+
"step": 50
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.9454545454545454,
|
| 388 |
+
"grad_norm": 0.001054088119417429,
|
| 389 |
+
"learning_rate": 0.00013319075811618129,
|
| 390 |
+
"loss": 4.1589,
|
| 391 |
+
"step": 52
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.9454545454545454,
|
| 395 |
+
"eval_loss": 4.093936443328857,
|
| 396 |
+
"eval_runtime": 136.0542,
|
| 397 |
+
"eval_samples_per_second": 2.573,
|
| 398 |
+
"eval_steps_per_second": 0.044,
|
| 399 |
+
"step": 52
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.9818181818181818,
|
| 403 |
+
"grad_norm": 0.0010858627501875162,
|
| 404 |
+
"learning_rate": 0.00012859797335355435,
|
| 405 |
+
"loss": 4.1589,
|
| 406 |
+
"step": 54
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9818181818181818,
|
| 410 |
+
"eval_loss": 4.093936443328857,
|
| 411 |
+
"eval_runtime": 110.1319,
|
| 412 |
+
"eval_samples_per_second": 3.178,
|
| 413 |
+
"eval_steps_per_second": 0.054,
|
| 414 |
+
"step": 54
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.018181818181818,
|
| 418 |
+
"grad_norm": 0.001234299037605524,
|
| 419 |
+
"learning_rate": 0.0001240051885909274,
|
| 420 |
+
"loss": 3.96,
|
| 421 |
+
"step": 56
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.018181818181818,
|
| 425 |
+
"eval_loss": 4.093935966491699,
|
| 426 |
+
"eval_runtime": 118.108,
|
| 427 |
+
"eval_samples_per_second": 2.963,
|
| 428 |
+
"eval_steps_per_second": 0.051,
|
| 429 |
+
"step": 56
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.0545454545454545,
|
| 433 |
+
"grad_norm": 0.0017606632318347692,
|
| 434 |
+
"learning_rate": 0.00011941240382830047,
|
| 435 |
+
"loss": 4.1588,
|
| 436 |
+
"step": 58
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0545454545454545,
|
| 440 |
+
"eval_loss": 4.093935012817383,
|
| 441 |
+
"eval_runtime": 111.0724,
|
| 442 |
+
"eval_samples_per_second": 3.151,
|
| 443 |
+
"eval_steps_per_second": 0.054,
|
| 444 |
+
"step": 58
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0909090909090908,
|
| 448 |
+
"grad_norm": 0.0012147607048973441,
|
| 449 |
+
"learning_rate": 0.00011481961906567352,
|
| 450 |
+
"loss": 4.1589,
|
| 451 |
+
"step": 60
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0909090909090908,
|
| 455 |
+
"eval_loss": 4.093934535980225,
|
| 456 |
+
"eval_runtime": 123.0725,
|
| 457 |
+
"eval_samples_per_second": 2.844,
|
| 458 |
+
"eval_steps_per_second": 0.049,
|
| 459 |
+
"step": 60
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.1272727272727272,
|
| 463 |
+
"grad_norm": 0.0010563035029917955,
|
| 464 |
+
"learning_rate": 0.00011022683430304658,
|
| 465 |
+
"loss": 4.1589,
|
| 466 |
+
"step": 62
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.1272727272727272,
|
| 470 |
+
"eval_loss": 4.093933582305908,
|
| 471 |
+
"eval_runtime": 130.8184,
|
| 472 |
+
"eval_samples_per_second": 2.675,
|
| 473 |
+
"eval_steps_per_second": 0.046,
|
| 474 |
+
"step": 62
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.1636363636363636,
|
| 478 |
+
"grad_norm": 0.000990673084743321,
|
| 479 |
+
"learning_rate": 0.00010563404954041964,
|
| 480 |
+
"loss": 4.1589,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.1636363636363636,
|
| 485 |
+
"eval_loss": 4.093933582305908,
|
| 486 |
+
"eval_runtime": 130.543,
|
| 487 |
+
"eval_samples_per_second": 2.681,
|
| 488 |
+
"eval_steps_per_second": 0.046,
|
| 489 |
+
"step": 64
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.2,
|
| 493 |
+
"grad_norm": 0.0012123591732233763,
|
| 494 |
+
"learning_rate": 0.0001010412647777927,
|
| 495 |
+
"loss": 4.1589,
|
| 496 |
+
"step": 66
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.2,
|
| 500 |
+
"eval_loss": 4.09393310546875,
|
| 501 |
+
"eval_runtime": 153.4481,
|
| 502 |
+
"eval_samples_per_second": 2.281,
|
| 503 |
+
"eval_steps_per_second": 0.039,
|
| 504 |
+
"step": 66
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.2363636363636363,
|
| 508 |
+
"grad_norm": 0.0011688098311424255,
|
| 509 |
+
"learning_rate": 9.644848001516577e-05,
|
| 510 |
+
"loss": 4.1589,
|
| 511 |
+
"step": 68
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.2363636363636363,
|
| 515 |
+
"eval_loss": 4.093932151794434,
|
| 516 |
+
"eval_runtime": 154.5442,
|
| 517 |
+
"eval_samples_per_second": 2.265,
|
| 518 |
+
"eval_steps_per_second": 0.039,
|
| 519 |
+
"step": 68
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.2727272727272727,
|
| 523 |
+
"grad_norm": 0.0015955213457345963,
|
| 524 |
+
"learning_rate": 9.185569525253883e-05,
|
| 525 |
+
"loss": 4.1589,
|
| 526 |
+
"step": 70
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.2727272727272727,
|
| 530 |
+
"eval_loss": 4.093931674957275,
|
| 531 |
+
"eval_runtime": 122.1283,
|
| 532 |
+
"eval_samples_per_second": 2.866,
|
| 533 |
+
"eval_steps_per_second": 0.049,
|
| 534 |
+
"step": 70
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.309090909090909,
|
| 538 |
+
"grad_norm": 0.001243259641341865,
|
| 539 |
+
"learning_rate": 8.726291048991188e-05,
|
| 540 |
+
"loss": 4.1589,
|
| 541 |
+
"step": 72
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.309090909090909,
|
| 545 |
+
"eval_loss": 4.093931198120117,
|
| 546 |
+
"eval_runtime": 123.0656,
|
| 547 |
+
"eval_samples_per_second": 2.844,
|
| 548 |
+
"eval_steps_per_second": 0.049,
|
| 549 |
+
"step": 72
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.3454545454545455,
|
| 553 |
+
"grad_norm": 0.001263299840502441,
|
| 554 |
+
"learning_rate": 8.267012572728494e-05,
|
| 555 |
+
"loss": 4.1589,
|
| 556 |
+
"step": 74
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.3454545454545455,
|
| 560 |
+
"eval_loss": 4.093930721282959,
|
| 561 |
+
"eval_runtime": 115.4851,
|
| 562 |
+
"eval_samples_per_second": 3.031,
|
| 563 |
+
"eval_steps_per_second": 0.052,
|
| 564 |
+
"step": 74
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.3818181818181818,
|
| 568 |
+
"grad_norm": 0.0013924150262027979,
|
| 569 |
+
"learning_rate": 7.8077340964658e-05,
|
| 570 |
+
"loss": 4.1588,
|
| 571 |
+
"step": 76
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.3818181818181818,
|
| 575 |
+
"eval_loss": 4.093929767608643,
|
| 576 |
+
"eval_runtime": 139.7759,
|
| 577 |
+
"eval_samples_per_second": 2.504,
|
| 578 |
+
"eval_steps_per_second": 0.043,
|
| 579 |
+
"step": 76
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.4181818181818182,
|
| 583 |
+
"grad_norm": 0.001308809733018279,
|
| 584 |
+
"learning_rate": 7.348455620203105e-05,
|
| 585 |
+
"loss": 4.1588,
|
| 586 |
+
"step": 78
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.4181818181818182,
|
| 590 |
+
"eval_loss": 4.093928337097168,
|
| 591 |
+
"eval_runtime": 110.3532,
|
| 592 |
+
"eval_samples_per_second": 3.172,
|
| 593 |
+
"eval_steps_per_second": 0.054,
|
| 594 |
+
"step": 78
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.4545454545454546,
|
| 598 |
+
"grad_norm": 0.00145295774564147,
|
| 599 |
+
"learning_rate": 6.889177143940411e-05,
|
| 600 |
+
"loss": 4.1588,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.4545454545454546,
|
| 605 |
+
"eval_loss": 4.093928337097168,
|
| 606 |
+
"eval_runtime": 110.6229,
|
| 607 |
+
"eval_samples_per_second": 3.164,
|
| 608 |
+
"eval_steps_per_second": 0.054,
|
| 609 |
+
"step": 80
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.490909090909091,
|
| 613 |
+
"grad_norm": 0.0014558923430740833,
|
| 614 |
+
"learning_rate": 6.429898667677717e-05,
|
| 615 |
+
"loss": 4.1588,
|
| 616 |
+
"step": 82
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.490909090909091,
|
| 620 |
+
"eval_loss": 4.09392786026001,
|
| 621 |
+
"eval_runtime": 151.2194,
|
| 622 |
+
"eval_samples_per_second": 2.315,
|
| 623 |
+
"eval_steps_per_second": 0.04,
|
| 624 |
+
"step": 82
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.5272727272727273,
|
| 628 |
+
"grad_norm": 0.0015545696951448917,
|
| 629 |
+
"learning_rate": 5.9706201914150236e-05,
|
| 630 |
+
"loss": 4.1588,
|
| 631 |
+
"step": 84
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.5272727272727273,
|
| 635 |
+
"eval_loss": 4.093926906585693,
|
| 636 |
+
"eval_runtime": 131.734,
|
| 637 |
+
"eval_samples_per_second": 2.657,
|
| 638 |
+
"eval_steps_per_second": 0.046,
|
| 639 |
+
"step": 84
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.5636363636363635,
|
| 643 |
+
"grad_norm": 0.0016734582604840398,
|
| 644 |
+
"learning_rate": 5.511341715152329e-05,
|
| 645 |
+
"loss": 4.1588,
|
| 646 |
+
"step": 86
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.5636363636363635,
|
| 650 |
+
"eval_loss": 4.093926429748535,
|
| 651 |
+
"eval_runtime": 109.3531,
|
| 652 |
+
"eval_samples_per_second": 3.201,
|
| 653 |
+
"eval_steps_per_second": 0.055,
|
| 654 |
+
"step": 86
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.6,
|
| 658 |
+
"grad_norm": 0.0014604291645810008,
|
| 659 |
+
"learning_rate": 5.052063238889635e-05,
|
| 660 |
+
"loss": 4.1589,
|
| 661 |
+
"step": 88
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.6,
|
| 665 |
+
"eval_loss": 4.093925952911377,
|
| 666 |
+
"eval_runtime": 109.4141,
|
| 667 |
+
"eval_samples_per_second": 3.199,
|
| 668 |
+
"eval_steps_per_second": 0.055,
|
| 669 |
+
"step": 88
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.6363636363636362,
|
| 673 |
+
"grad_norm": 0.0015530511736869812,
|
| 674 |
+
"learning_rate": 4.5927847626269415e-05,
|
| 675 |
+
"loss": 4.1588,
|
| 676 |
+
"step": 90
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.6363636363636362,
|
| 680 |
+
"eval_loss": 4.093925476074219,
|
| 681 |
+
"eval_runtime": 109.4483,
|
| 682 |
+
"eval_samples_per_second": 3.198,
|
| 683 |
+
"eval_steps_per_second": 0.055,
|
| 684 |
+
"step": 90
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.6727272727272728,
|
| 688 |
+
"grad_norm": 0.0015709660947322845,
|
| 689 |
+
"learning_rate": 4.133506286364247e-05,
|
| 690 |
+
"loss": 4.1589,
|
| 691 |
+
"step": 92
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.6727272727272728,
|
| 695 |
+
"eval_loss": 4.0939249992370605,
|
| 696 |
+
"eval_runtime": 122.4435,
|
| 697 |
+
"eval_samples_per_second": 2.858,
|
| 698 |
+
"eval_steps_per_second": 0.049,
|
| 699 |
+
"step": 92
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.709090909090909,
|
| 703 |
+
"grad_norm": 0.0014102915301918983,
|
| 704 |
+
"learning_rate": 3.6742278101015525e-05,
|
| 705 |
+
"loss": 4.1588,
|
| 706 |
+
"step": 94
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.709090909090909,
|
| 710 |
+
"eval_loss": 4.093924522399902,
|
| 711 |
+
"eval_runtime": 150.6921,
|
| 712 |
+
"eval_samples_per_second": 2.323,
|
| 713 |
+
"eval_steps_per_second": 0.04,
|
| 714 |
+
"step": 94
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.7454545454545456,
|
| 718 |
+
"grad_norm": 0.0015738351503387094,
|
| 719 |
+
"learning_rate": 3.214949333838859e-05,
|
| 720 |
+
"loss": 4.1588,
|
| 721 |
+
"step": 96
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.7454545454545456,
|
| 725 |
+
"eval_loss": 4.093923568725586,
|
| 726 |
+
"eval_runtime": 128.0266,
|
| 727 |
+
"eval_samples_per_second": 2.734,
|
| 728 |
+
"eval_steps_per_second": 0.047,
|
| 729 |
+
"step": 96
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.7818181818181817,
|
| 733 |
+
"grad_norm": 0.001314620254561305,
|
| 734 |
+
"learning_rate": 2.7556708575761645e-05,
|
| 735 |
+
"loss": 4.1588,
|
| 736 |
+
"step": 98
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.7818181818181817,
|
| 740 |
+
"eval_loss": 4.093923091888428,
|
| 741 |
+
"eval_runtime": 110.6007,
|
| 742 |
+
"eval_samples_per_second": 3.165,
|
| 743 |
+
"eval_steps_per_second": 0.054,
|
| 744 |
+
"step": 98
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.8181818181818183,
|
| 748 |
+
"grad_norm": 0.0014478659722954035,
|
| 749 |
+
"learning_rate": 2.2963923813134707e-05,
|
| 750 |
+
"loss": 4.1589,
|
| 751 |
+
"step": 100
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.8181818181818183,
|
| 755 |
+
"eval_loss": 4.0939226150512695,
|
| 756 |
+
"eval_runtime": 124.9794,
|
| 757 |
+
"eval_samples_per_second": 2.8,
|
| 758 |
+
"eval_steps_per_second": 0.048,
|
| 759 |
+
"step": 100
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.8545454545454545,
|
| 763 |
+
"grad_norm": 0.0018716281047090888,
|
| 764 |
+
"learning_rate": 1.8371139050507763e-05,
|
| 765 |
+
"loss": 4.1588,
|
| 766 |
+
"step": 102
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.8545454545454545,
|
| 770 |
+
"eval_loss": 4.093922138214111,
|
| 771 |
+
"eval_runtime": 108.7929,
|
| 772 |
+
"eval_samples_per_second": 3.217,
|
| 773 |
+
"eval_steps_per_second": 0.055,
|
| 774 |
+
"step": 102
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.8909090909090909,
|
| 778 |
+
"grad_norm": 0.0020189164206385612,
|
| 779 |
+
"learning_rate": 1.3778354287880823e-05,
|
| 780 |
+
"loss": 4.1588,
|
| 781 |
+
"step": 104
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.8909090909090909,
|
| 785 |
+
"eval_loss": 4.093922138214111,
|
| 786 |
+
"eval_runtime": 157.5843,
|
| 787 |
+
"eval_samples_per_second": 2.221,
|
| 788 |
+
"eval_steps_per_second": 0.038,
|
| 789 |
+
"step": 104
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.9272727272727272,
|
| 793 |
+
"grad_norm": 0.0016775216208770871,
|
| 794 |
+
"learning_rate": 9.185569525253881e-06,
|
| 795 |
+
"loss": 4.1588,
|
| 796 |
+
"step": 106
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.9272727272727272,
|
| 800 |
+
"eval_loss": 4.093922138214111,
|
| 801 |
+
"eval_runtime": 130.985,
|
| 802 |
+
"eval_samples_per_second": 2.672,
|
| 803 |
+
"eval_steps_per_second": 0.046,
|
| 804 |
+
"step": 106
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.9636363636363636,
|
| 808 |
+
"grad_norm": 0.0019341203151270747,
|
| 809 |
+
"learning_rate": 4.592784762626941e-06,
|
| 810 |
+
"loss": 4.1588,
|
| 811 |
+
"step": 108
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.9636363636363636,
|
| 815 |
+
"eval_loss": 4.093922138214111,
|
| 816 |
+
"eval_runtime": 183.7417,
|
| 817 |
+
"eval_samples_per_second": 1.905,
|
| 818 |
+
"eval_steps_per_second": 0.033,
|
| 819 |
+
"step": 108
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.0,
|
| 823 |
+
"grad_norm": 0.0019428413361310959,
|
| 824 |
+
"learning_rate": 0.0,
|
| 825 |
+
"loss": 3.96,
|
| 826 |
+
"step": 110
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.0,
|
| 830 |
+
"eval_loss": 4.093922138214111,
|
| 831 |
+
"eval_runtime": 121.5213,
|
| 832 |
+
"eval_samples_per_second": 2.88,
|
| 833 |
+
"eval_steps_per_second": 0.049,
|
| 834 |
+
"step": 110
|
| 835 |
+
}
|
| 836 |
+
],
|
| 837 |
+
"logging_steps": 2,
|
| 838 |
+
"max_steps": 110,
|
| 839 |
+
"num_input_tokens_seen": 0,
|
| 840 |
+
"num_train_epochs": 2,
|
| 841 |
+
"save_steps": 500,
|
| 842 |
+
"stateful_callbacks": {
|
| 843 |
+
"TrainerControl": {
|
| 844 |
+
"args": {
|
| 845 |
+
"should_epoch_stop": false,
|
| 846 |
+
"should_evaluate": false,
|
| 847 |
+
"should_log": false,
|
| 848 |
+
"should_save": true,
|
| 849 |
+
"should_training_stop": true
|
| 850 |
+
},
|
| 851 |
+
"attributes": {}
|
| 852 |
+
}
|
| 853 |
+
},
|
| 854 |
+
"total_flos": 407052651766068.0,
|
| 855 |
+
"train_batch_size": 64,
|
| 856 |
+
"trial_name": null,
|
| 857 |
+
"trial_params": {
|
| 858 |
+
"_wandb": {},
|
| 859 |
+
"assignments": {},
|
| 860 |
+
"decay": 0.1,
|
| 861 |
+
"learning_rate": 0.00025260316194448176,
|
| 862 |
+
"metric": "eval/loss",
|
| 863 |
+
"per_device_train_batch_size": 64
|
| 864 |
+
}
|
| 865 |
+
}
|
run-wgja68lo/checkpoint-110/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f10dc52d742b958935413d6f7dc245cb806eaebf68214cd06171241af4d4a13
|
| 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 sha256:1f10dc52d742b958935413d6f7dc245cb806eaebf68214cd06171241af4d4a13
|
| 3 |
size 5112
|