Upload folder using huggingface_hub
Browse files- checkpoints/checkpoint-21651/ema.safetensors +3 -0
- checkpoints/checkpoint-21651/model.safetensors +3 -0
- checkpoints/checkpoint-21651/optimizer.pt +3 -0
- checkpoints/checkpoint-21651/rng_state.pth +3 -0
- checkpoints/checkpoint-21651/scaler.pt +3 -0
- checkpoints/checkpoint-21651/scheduler.pt +3 -0
- checkpoints/checkpoint-21651/trainer_state.json +937 -0
- checkpoints/checkpoint-21651/training_args.bin +3 -0
checkpoints/checkpoint-21651/ema.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feaea8def4267d7feb8cdf3fa3b5e5783c1d9ec500b941ac06d1d3ba82f8388d
|
| 3 |
+
size 634904
|
checkpoints/checkpoint-21651/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93d2c6522a514560e4df605c64e92cb78dac8fe345eba6a8eca9ecd6f292870a
|
| 3 |
+
size 19272752
|
checkpoints/checkpoint-21651/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa293976ee742dd2f3feb412e7fc165c5c4169ba85540aafda7ad68ce306239
|
| 3 |
+
size 1337227
|
checkpoints/checkpoint-21651/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cbe65e3891168fa6d91b79ffd0ce826f20fd596a538e5897552ab55ecbe73a0
|
| 3 |
+
size 14645
|
checkpoints/checkpoint-21651/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b4840253f689f85b53507bf8bfcf7219c70eaf98d96eb849f5c45b1fe52ac00
|
| 3 |
+
size 1383
|
checkpoints/checkpoint-21651/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ff448be4b4d90a62cca3d12f4b0e7a0f6acf476b040d09aac40be4d55ce181c
|
| 3 |
+
size 1465
|
checkpoints/checkpoint-21651/trainer_state.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 1024,
|
| 7 |
+
"global_step": 21651,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011823934229365849,
|
| 14 |
+
"grad_norm": 0.11696221679449081,
|
| 15 |
+
"learning_rate": 9.418282548476454e-05,
|
| 16 |
+
"loss": 1.568,
|
| 17 |
+
"step": 256
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.023647868458731697,
|
| 21 |
+
"grad_norm": 0.14284025132656097,
|
| 22 |
+
"learning_rate": 0.00018873499538319484,
|
| 23 |
+
"loss": 1.4627,
|
| 24 |
+
"step": 512
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03547180268809755,
|
| 28 |
+
"grad_norm": 0.14623360335826874,
|
| 29 |
+
"learning_rate": 0.00028328716528162515,
|
| 30 |
+
"loss": 1.3763,
|
| 31 |
+
"step": 768
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.047295736917463395,
|
| 35 |
+
"grad_norm": 0.1999262273311615,
|
| 36 |
+
"learning_rate": 0.0003778393351800554,
|
| 37 |
+
"loss": 1.325,
|
| 38 |
+
"step": 1024
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.047295736917463395,
|
| 42 |
+
"eval_loss": 1.2694775628172643,
|
| 43 |
+
"eval_mse_loss": 1.2694775628172643,
|
| 44 |
+
"step": 1024
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.047295736917463395,
|
| 48 |
+
"eval_loss": 1.2694775628172643,
|
| 49 |
+
"eval_mse_loss": 1.2694775628172643,
|
| 50 |
+
"eval_runtime": 99.7615,
|
| 51 |
+
"eval_samples_per_second": 280.599,
|
| 52 |
+
"eval_steps_per_second": 4.39,
|
| 53 |
+
"step": 1024
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.05911967114682925,
|
| 57 |
+
"grad_norm": 0.17195427417755127,
|
| 58 |
+
"learning_rate": 0.000399910381984159,
|
| 59 |
+
"loss": 1.2775,
|
| 60 |
+
"step": 1280
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0709436053761951,
|
| 64 |
+
"grad_norm": 0.24726267158985138,
|
| 65 |
+
"learning_rate": 0.0003995235470960099,
|
| 66 |
+
"loss": 1.2335,
|
| 67 |
+
"step": 1536
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.08276753960556095,
|
| 71 |
+
"grad_norm": 0.29991263151168823,
|
| 72 |
+
"learning_rate": 0.000398831687956263,
|
| 73 |
+
"loss": 1.2043,
|
| 74 |
+
"step": 1792
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.09459147383492679,
|
| 78 |
+
"grad_norm": 0.2526465356349945,
|
| 79 |
+
"learning_rate": 0.00039783586225369426,
|
| 80 |
+
"loss": 1.1758,
|
| 81 |
+
"step": 2048
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.09459147383492679,
|
| 85 |
+
"eval_loss": 1.1193939001048536,
|
| 86 |
+
"eval_mse_loss": 1.1193939001048536,
|
| 87 |
+
"step": 2048
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09459147383492679,
|
| 91 |
+
"eval_loss": 1.1193939001048536,
|
| 92 |
+
"eval_mse_loss": 1.1193939001048536,
|
| 93 |
+
"eval_runtime": 99.592,
|
| 94 |
+
"eval_samples_per_second": 281.077,
|
| 95 |
+
"eval_steps_per_second": 4.398,
|
| 96 |
+
"step": 2048
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.10641540806429264,
|
| 100 |
+
"grad_norm": 0.23426194489002228,
|
| 101 |
+
"learning_rate": 0.0003965375923699678,
|
| 102 |
+
"loss": 1.1514,
|
| 103 |
+
"step": 2304
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.1182393422936585,
|
| 107 |
+
"grad_norm": 0.2490096390247345,
|
| 108 |
+
"learning_rate": 0.0003949388630522747,
|
| 109 |
+
"loss": 1.1287,
|
| 110 |
+
"step": 2560
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.13006327652302435,
|
| 114 |
+
"grad_norm": 0.3001377582550049,
|
| 115 |
+
"learning_rate": 0.0003930421183791246,
|
| 116 |
+
"loss": 1.1064,
|
| 117 |
+
"step": 2816
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1418872107523902,
|
| 121 |
+
"grad_norm": 0.31271305680274963,
|
| 122 |
+
"learning_rate": 0.00039085025802392876,
|
| 123 |
+
"loss": 1.0907,
|
| 124 |
+
"step": 3072
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.1418872107523902,
|
| 128 |
+
"eval_loss": 1.0367718265481192,
|
| 129 |
+
"eval_mse_loss": 1.0367718265481192,
|
| 130 |
+
"step": 3072
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.1418872107523902,
|
| 134 |
+
"eval_loss": 1.0367718265481192,
|
| 135 |
+
"eval_mse_loss": 1.0367718265481192,
|
| 136 |
+
"eval_runtime": 99.0318,
|
| 137 |
+
"eval_samples_per_second": 282.667,
|
| 138 |
+
"eval_steps_per_second": 4.423,
|
| 139 |
+
"step": 3072
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.15371114498175603,
|
| 143 |
+
"grad_norm": 0.31617286801338196,
|
| 144 |
+
"learning_rate": 0.0003883666328220855,
|
| 145 |
+
"loss": 1.0795,
|
| 146 |
+
"step": 3328
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.1655350792111219,
|
| 150 |
+
"grad_norm": 0.3006609082221985,
|
| 151 |
+
"learning_rate": 0.00038559503964834713,
|
| 152 |
+
"loss": 1.072,
|
| 153 |
+
"step": 3584
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.17735901344048774,
|
| 157 |
+
"grad_norm": 0.3017251491546631,
|
| 158 |
+
"learning_rate": 0.00038253971561229733,
|
| 159 |
+
"loss": 1.0632,
|
| 160 |
+
"step": 3840
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.18918294766985358,
|
| 164 |
+
"grad_norm": 0.29505959153175354,
|
| 165 |
+
"learning_rate": 0.00037920533158081383,
|
| 166 |
+
"loss": 1.0583,
|
| 167 |
+
"step": 4096
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.18918294766985358,
|
| 171 |
+
"eval_loss": 1.0053560841301261,
|
| 172 |
+
"eval_mse_loss": 1.0053560841301261,
|
| 173 |
+
"step": 4096
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.18918294766985358,
|
| 177 |
+
"eval_loss": 1.0053560841301261,
|
| 178 |
+
"eval_mse_loss": 1.0053560841301261,
|
| 179 |
+
"eval_runtime": 99.7606,
|
| 180 |
+
"eval_samples_per_second": 280.602,
|
| 181 |
+
"eval_steps_per_second": 4.391,
|
| 182 |
+
"step": 4096
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.20100688189921945,
|
| 186 |
+
"grad_norm": 0.327700138092041,
|
| 187 |
+
"learning_rate": 0.00037559698503741954,
|
| 188 |
+
"loss": 1.0539,
|
| 189 |
+
"step": 4352
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.2128308161285853,
|
| 193 |
+
"grad_norm": 0.3910951316356659,
|
| 194 |
+
"learning_rate": 0.0003717201922894372,
|
| 195 |
+
"loss": 1.0525,
|
| 196 |
+
"step": 4608
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.22465475035795113,
|
| 200 |
+
"grad_norm": 0.3237537443637848,
|
| 201 |
+
"learning_rate": 0.0003675808800348619,
|
| 202 |
+
"loss": 1.0461,
|
| 203 |
+
"step": 4864
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.236478684587317,
|
| 207 |
+
"grad_norm": 0.4316788911819458,
|
| 208 |
+
"learning_rate": 0.0003631853763018435,
|
| 209 |
+
"loss": 1.042,
|
| 210 |
+
"step": 5120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.236478684587317,
|
| 214 |
+
"eval_loss": 0.9950277422933274,
|
| 215 |
+
"eval_mse_loss": 0.9950277422933274,
|
| 216 |
+
"step": 5120
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.236478684587317,
|
| 220 |
+
"eval_loss": 0.9950277422933274,
|
| 221 |
+
"eval_mse_loss": 0.9950277422933274,
|
| 222 |
+
"eval_runtime": 99.7527,
|
| 223 |
+
"eval_samples_per_second": 280.624,
|
| 224 |
+
"eval_steps_per_second": 4.391,
|
| 225 |
+
"step": 5120
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.24830261881668284,
|
| 229 |
+
"grad_norm": 0.32822364568710327,
|
| 230 |
+
"learning_rate": 0.0003585404007746302,
|
| 231 |
+
"loss": 1.0385,
|
| 232 |
+
"step": 5376
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.2601265530460487,
|
| 236 |
+
"grad_norm": 0.40738987922668457,
|
| 237 |
+
"learning_rate": 0.0003536530545207627,
|
| 238 |
+
"loss": 1.0378,
|
| 239 |
+
"step": 5632
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.27195048727541454,
|
| 243 |
+
"grad_norm": 0.318866103887558,
|
| 244 |
+
"learning_rate": 0.0003485308091352234,
|
| 245 |
+
"loss": 1.0375,
|
| 246 |
+
"step": 5888
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.2837744215047804,
|
| 250 |
+
"grad_norm": 0.34148862957954407,
|
| 251 |
+
"learning_rate": 0.0003431814953181376,
|
| 252 |
+
"loss": 1.0351,
|
| 253 |
+
"step": 6144
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.2837744215047804,
|
| 257 |
+
"eval_loss": 0.9900110875634842,
|
| 258 |
+
"eval_mse_loss": 0.9900110875634842,
|
| 259 |
+
"step": 6144
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.2837744215047804,
|
| 263 |
+
"eval_loss": 0.9900110875634842,
|
| 264 |
+
"eval_mse_loss": 0.9900110875634842,
|
| 265 |
+
"eval_runtime": 99.6906,
|
| 266 |
+
"eval_samples_per_second": 280.799,
|
| 267 |
+
"eval_steps_per_second": 4.394,
|
| 268 |
+
"step": 6144
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2955983557341462,
|
| 272 |
+
"grad_norm": 0.2927286624908447,
|
| 273 |
+
"learning_rate": 0.0003376132909034871,
|
| 274 |
+
"loss": 1.0342,
|
| 275 |
+
"step": 6400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.30742228996351206,
|
| 279 |
+
"grad_norm": 0.3355765640735626,
|
| 280 |
+
"learning_rate": 0.000331834708357139,
|
| 281 |
+
"loss": 1.0334,
|
| 282 |
+
"step": 6656
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3192462241928779,
|
| 286 |
+
"grad_norm": 0.3341493308544159,
|
| 287 |
+
"learning_rate": 0.00032585458176330104,
|
| 288 |
+
"loss": 1.0315,
|
| 289 |
+
"step": 6912
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3310701584222438,
|
| 293 |
+
"grad_norm": 0.3863889276981354,
|
| 294 |
+
"learning_rate": 0.0003196820533192994,
|
| 295 |
+
"loss": 1.0316,
|
| 296 |
+
"step": 7168
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3310701584222438,
|
| 300 |
+
"eval_loss": 0.9869283731669596,
|
| 301 |
+
"eval_mse_loss": 0.9869283731669596,
|
| 302 |
+
"step": 7168
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3310701584222438,
|
| 306 |
+
"eval_loss": 0.9869283731669596,
|
| 307 |
+
"eval_mse_loss": 0.9869283731669596,
|
| 308 |
+
"eval_runtime": 99.9137,
|
| 309 |
+
"eval_samples_per_second": 280.172,
|
| 310 |
+
"eval_steps_per_second": 4.384,
|
| 311 |
+
"step": 7168
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.34289409265160964,
|
| 315 |
+
"grad_norm": 0.37314340472221375,
|
| 316 |
+
"learning_rate": 0.00031332655935932356,
|
| 317 |
+
"loss": 1.0304,
|
| 318 |
+
"step": 7424
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3547180268809755,
|
| 322 |
+
"grad_norm": 0.31663990020751953,
|
| 323 |
+
"learning_rate": 0.0003067978159285067,
|
| 324 |
+
"loss": 1.0291,
|
| 325 |
+
"step": 7680
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3665419611103413,
|
| 329 |
+
"grad_norm": 0.3562430143356323,
|
| 330 |
+
"learning_rate": 0.0003001058039293929,
|
| 331 |
+
"loss": 1.0282,
|
| 332 |
+
"step": 7936
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.37836589533970716,
|
| 336 |
+
"grad_norm": 0.32352393865585327,
|
| 337 |
+
"learning_rate": 0.0002932607538635016,
|
| 338 |
+
"loss": 1.0289,
|
| 339 |
+
"step": 8192
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.37836589533970716,
|
| 343 |
+
"eval_loss": 0.9830868584380302,
|
| 344 |
+
"eval_mse_loss": 0.9830868584380302,
|
| 345 |
+
"step": 8192
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.37836589533970716,
|
| 349 |
+
"eval_loss": 0.9830868584380302,
|
| 350 |
+
"eval_mse_loss": 0.9830868584380302,
|
| 351 |
+
"eval_runtime": 100.3923,
|
| 352 |
+
"eval_samples_per_second": 278.836,
|
| 353 |
+
"eval_steps_per_second": 4.363,
|
| 354 |
+
"step": 8192
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.390189829569073,
|
| 358 |
+
"grad_norm": 0.3661426603794098,
|
| 359 |
+
"learning_rate": 0.0002862731301913133,
|
| 360 |
+
"loss": 1.0279,
|
| 361 |
+
"step": 8448
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.4020137637984389,
|
| 365 |
+
"grad_norm": 0.3046676218509674,
|
| 366 |
+
"learning_rate": 0.0002791536153345875,
|
| 367 |
+
"loss": 1.0275,
|
| 368 |
+
"step": 8704
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.41383769802780473,
|
| 372 |
+
"grad_norm": 0.3376181721687317,
|
| 373 |
+
"learning_rate": 0.0002719130933454701,
|
| 374 |
+
"loss": 1.0282,
|
| 375 |
+
"step": 8960
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.4256616322571706,
|
| 379 |
+
"grad_norm": 0.3915064334869385,
|
| 380 |
+
"learning_rate": 0.00026456263326735493,
|
| 381 |
+
"loss": 1.0307,
|
| 382 |
+
"step": 9216
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.4256616322571706,
|
| 386 |
+
"eval_loss": 0.984883288406346,
|
| 387 |
+
"eval_mse_loss": 0.984883288406346,
|
| 388 |
+
"step": 9216
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.4256616322571706,
|
| 392 |
+
"eval_loss": 0.984883288406346,
|
| 393 |
+
"eval_mse_loss": 0.984883288406346,
|
| 394 |
+
"eval_runtime": 100.2629,
|
| 395 |
+
"eval_samples_per_second": 279.196,
|
| 396 |
+
"eval_steps_per_second": 4.369,
|
| 397 |
+
"step": 9216
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.4374855664865364,
|
| 401 |
+
"grad_norm": 0.33798637986183167,
|
| 402 |
+
"learning_rate": 0.0002571134722129381,
|
| 403 |
+
"loss": 1.0297,
|
| 404 |
+
"step": 9472
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.44930950071590225,
|
| 408 |
+
"grad_norm": 0.2875025272369385,
|
| 409 |
+
"learning_rate": 0.0002495769981853336,
|
| 410 |
+
"loss": 1.0315,
|
| 411 |
+
"step": 9728
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.4611334349452681,
|
| 415 |
+
"grad_norm": 0.33755892515182495,
|
| 416 |
+
"learning_rate": 0.0002419647326685136,
|
| 417 |
+
"loss": 1.031,
|
| 418 |
+
"step": 9984
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.472957369174634,
|
| 422 |
+
"grad_norm": 0.2760786712169647,
|
| 423 |
+
"learning_rate": 0.00023431840867685062,
|
| 424 |
+
"loss": 1.0319,
|
| 425 |
+
"step": 10240
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.472957369174634,
|
| 429 |
+
"eval_loss": 0.9867455217664101,
|
| 430 |
+
"eval_mse_loss": 0.9867455217664101,
|
| 431 |
+
"step": 10240
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.472957369174634,
|
| 435 |
+
"eval_loss": 0.9867455217664101,
|
| 436 |
+
"eval_mse_loss": 0.9867455217664101,
|
| 437 |
+
"eval_runtime": 100.0615,
|
| 438 |
+
"eval_samples_per_second": 279.758,
|
| 439 |
+
"eval_steps_per_second": 4.377,
|
| 440 |
+
"step": 10240
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.48478130340399983,
|
| 444 |
+
"grad_norm": 0.3291190266609192,
|
| 445 |
+
"learning_rate": 0.00022658975213149085,
|
| 446 |
+
"loss": 1.0324,
|
| 447 |
+
"step": 10496
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.49660523763336567,
|
| 451 |
+
"grad_norm": 0.3030407130718231,
|
| 452 |
+
"learning_rate": 0.00021882044615220646,
|
| 453 |
+
"loss": 1.0305,
|
| 454 |
+
"step": 10752
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5084291718627315,
|
| 458 |
+
"grad_norm": 0.2691882848739624,
|
| 459 |
+
"learning_rate": 0.00021105286996472446,
|
| 460 |
+
"loss": 1.0362,
|
| 461 |
+
"step": 11008
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.5202531060920974,
|
| 465 |
+
"grad_norm": 0.2871313989162445,
|
| 466 |
+
"learning_rate": 0.00020323798398011488,
|
| 467 |
+
"loss": 1.0375,
|
| 468 |
+
"step": 11264
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.5202531060920974,
|
| 472 |
+
"eval_loss": 0.9919488762067333,
|
| 473 |
+
"eval_mse_loss": 0.9919488762067333,
|
| 474 |
+
"step": 11264
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.5202531060920974,
|
| 478 |
+
"eval_loss": 0.9919488762067333,
|
| 479 |
+
"eval_mse_loss": 0.9919488762067333,
|
| 480 |
+
"eval_runtime": 99.6352,
|
| 481 |
+
"eval_samples_per_second": 280.955,
|
| 482 |
+
"eval_steps_per_second": 4.396,
|
| 483 |
+
"step": 11264
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.5320770403214632,
|
| 487 |
+
"grad_norm": 0.34249189496040344,
|
| 488 |
+
"learning_rate": 0.0001954181478848312,
|
| 489 |
+
"loss": 1.035,
|
| 490 |
+
"step": 11520
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.5439009745508291,
|
| 494 |
+
"grad_norm": 0.30227038264274597,
|
| 495 |
+
"learning_rate": 0.00018760531635634027,
|
| 496 |
+
"loss": 1.0401,
|
| 497 |
+
"step": 11776
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.5557249087801949,
|
| 501 |
+
"grad_norm": 0.3367672860622406,
|
| 502 |
+
"learning_rate": 0.0001798114333637852,
|
| 503 |
+
"loss": 1.0416,
|
| 504 |
+
"step": 12032
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.5675488430095608,
|
| 508 |
+
"grad_norm": 0.35392817854881287,
|
| 509 |
+
"learning_rate": 0.00017204841390848513,
|
| 510 |
+
"loss": 1.0407,
|
| 511 |
+
"step": 12288
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.5675488430095608,
|
| 515 |
+
"eval_loss": 1.0043473209692464,
|
| 516 |
+
"eval_mse_loss": 1.0043473209692464,
|
| 517 |
+
"step": 12288
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.5675488430095608,
|
| 521 |
+
"eval_loss": 1.0043473209692464,
|
| 522 |
+
"eval_mse_loss": 1.0043473209692464,
|
| 523 |
+
"eval_runtime": 99.386,
|
| 524 |
+
"eval_samples_per_second": 281.659,
|
| 525 |
+
"eval_steps_per_second": 4.407,
|
| 526 |
+
"step": 12288
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.5793727772389267,
|
| 530 |
+
"grad_norm": 0.2517242431640625,
|
| 531 |
+
"learning_rate": 0.00016432812580871982,
|
| 532 |
+
"loss": 1.0431,
|
| 533 |
+
"step": 12544
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.5911967114682924,
|
| 537 |
+
"grad_norm": 0.31317463517189026,
|
| 538 |
+
"learning_rate": 0.00015666237155664652,
|
| 539 |
+
"loss": 1.0451,
|
| 540 |
+
"step": 12800
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.6030206456976583,
|
| 544 |
+
"grad_norm": 0.27259454131126404,
|
| 545 |
+
"learning_rate": 0.00014906287027508398,
|
| 546 |
+
"loss": 1.0491,
|
| 547 |
+
"step": 13056
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.6148445799270241,
|
| 551 |
+
"grad_norm": 0.2674678862094879,
|
| 552 |
+
"learning_rate": 0.00014154123980174944,
|
| 553 |
+
"loss": 1.0467,
|
| 554 |
+
"step": 13312
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.6148445799270241,
|
| 558 |
+
"eval_loss": 1.0088394922480735,
|
| 559 |
+
"eval_mse_loss": 1.0088394922480735,
|
| 560 |
+
"step": 13312
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.6148445799270241,
|
| 564 |
+
"eval_loss": 1.0088394922480735,
|
| 565 |
+
"eval_mse_loss": 1.0088394922480735,
|
| 566 |
+
"eval_runtime": 100.1788,
|
| 567 |
+
"eval_samples_per_second": 279.43,
|
| 568 |
+
"eval_steps_per_second": 4.372,
|
| 569 |
+
"step": 13312
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.62666851415639,
|
| 573 |
+
"grad_norm": 0.3362578749656677,
|
| 574 |
+
"learning_rate": 0.00013410897892833596,
|
| 575 |
+
"loss": 1.049,
|
| 576 |
+
"step": 13568
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.6384924483857558,
|
| 580 |
+
"grad_norm": 0.26616010069847107,
|
| 581 |
+
"learning_rate": 0.00012677744982158334,
|
| 582 |
+
"loss": 1.0532,
|
| 583 |
+
"step": 13824
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.6503163826151217,
|
| 587 |
+
"grad_norm": 0.2684532403945923,
|
| 588 |
+
"learning_rate": 0.00011955786065321544,
|
| 589 |
+
"loss": 1.0556,
|
| 590 |
+
"step": 14080
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6621403168444876,
|
| 594 |
+
"grad_norm": 0.24931219220161438,
|
| 595 |
+
"learning_rate": 0.00011246124846530075,
|
| 596 |
+
"loss": 1.0575,
|
| 597 |
+
"step": 14336
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6621403168444876,
|
| 601 |
+
"eval_loss": 1.0203365499842656,
|
| 602 |
+
"eval_mse_loss": 1.0203365499842656,
|
| 603 |
+
"step": 14336
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6621403168444876,
|
| 607 |
+
"eval_loss": 1.0203365499842656,
|
| 608 |
+
"eval_mse_loss": 1.0203365499842656,
|
| 609 |
+
"eval_runtime": 99.6009,
|
| 610 |
+
"eval_samples_per_second": 281.052,
|
| 611 |
+
"eval_steps_per_second": 4.398,
|
| 612 |
+
"step": 14336
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6739642510738534,
|
| 616 |
+
"grad_norm": 0.2652958929538727,
|
| 617 |
+
"learning_rate": 0.00010549846229722837,
|
| 618 |
+
"loss": 1.0648,
|
| 619 |
+
"step": 14592
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6857881853032193,
|
| 623 |
+
"grad_norm": 0.2742628753185272,
|
| 624 |
+
"learning_rate": 9.868014660009637e-05,
|
| 625 |
+
"loss": 1.0651,
|
| 626 |
+
"step": 14848
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6976121195325851,
|
| 630 |
+
"grad_norm": 0.2334495335817337,
|
| 631 |
+
"learning_rate": 9.204243934249532e-05,
|
| 632 |
+
"loss": 1.0699,
|
| 633 |
+
"step": 15104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.709436053761951,
|
| 637 |
+
"grad_norm": 0.2503329813480377,
|
| 638 |
+
"learning_rate": 8.554343421704003e-05,
|
| 639 |
+
"loss": 1.0706,
|
| 640 |
+
"step": 15360
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.709436053761951,
|
| 644 |
+
"eval_loss": 1.030193983828096,
|
| 645 |
+
"eval_mse_loss": 1.030193983828096,
|
| 646 |
+
"step": 15360
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.709436053761951,
|
| 650 |
+
"eval_loss": 1.030193983828096,
|
| 651 |
+
"eval_mse_loss": 1.030193983828096,
|
| 652 |
+
"eval_runtime": 100.1105,
|
| 653 |
+
"eval_samples_per_second": 279.621,
|
| 654 |
+
"eval_steps_per_second": 4.375,
|
| 655 |
+
"step": 15360
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7212599879913169,
|
| 659 |
+
"grad_norm": 0.2387477457523346,
|
| 660 |
+
"learning_rate": 7.921940607463536e-05,
|
| 661 |
+
"loss": 1.0736,
|
| 662 |
+
"step": 15616
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.7330839222206826,
|
| 666 |
+
"grad_norm": 0.2524156868457794,
|
| 667 |
+
"learning_rate": 7.308002285663097e-05,
|
| 668 |
+
"loss": 1.0767,
|
| 669 |
+
"step": 15872
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7449078564500485,
|
| 673 |
+
"grad_norm": 0.23690827190876007,
|
| 674 |
+
"learning_rate": 6.713467022601562e-05,
|
| 675 |
+
"loss": 1.0788,
|
| 676 |
+
"step": 16128
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7567317906794143,
|
| 680 |
+
"grad_norm": 0.25175976753234863,
|
| 681 |
+
"learning_rate": 6.139243721896071e-05,
|
| 682 |
+
"loss": 1.0853,
|
| 683 |
+
"step": 16384
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.7567317906794143,
|
| 687 |
+
"eval_loss": 1.038661680809439,
|
| 688 |
+
"eval_mse_loss": 1.038661680809439,
|
| 689 |
+
"step": 16384
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7567317906794143,
|
| 693 |
+
"eval_loss": 1.038661680809439,
|
| 694 |
+
"eval_mse_loss": 1.038661680809439,
|
| 695 |
+
"eval_runtime": 100.1169,
|
| 696 |
+
"eval_samples_per_second": 279.603,
|
| 697 |
+
"eval_steps_per_second": 4.375,
|
| 698 |
+
"step": 16384
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.7685557249087802,
|
| 702 |
+
"grad_norm": 0.21369080245494843,
|
| 703 |
+
"learning_rate": 5.586210234983709e-05,
|
| 704 |
+
"loss": 1.0881,
|
| 705 |
+
"step": 16640
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.780379659138146,
|
| 709 |
+
"grad_norm": 0.20162087678909302,
|
| 710 |
+
"learning_rate": 5.057242299355618e-05,
|
| 711 |
+
"loss": 1.0924,
|
| 712 |
+
"step": 16896
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.7922035933675119,
|
| 716 |
+
"grad_norm": 0.24671520292758942,
|
| 717 |
+
"learning_rate": 4.549000344276444e-05,
|
| 718 |
+
"loss": 1.0936,
|
| 719 |
+
"step": 17152
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.8040275275968778,
|
| 723 |
+
"grad_norm": 0.21685843169689178,
|
| 724 |
+
"learning_rate": 4.0643793085073956e-05,
|
| 725 |
+
"loss": 1.0967,
|
| 726 |
+
"step": 17408
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.8040275275968778,
|
| 730 |
+
"eval_loss": 1.0570238397273843,
|
| 731 |
+
"eval_mse_loss": 1.0570238397273843,
|
| 732 |
+
"step": 17408
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.8040275275968778,
|
| 736 |
+
"eval_loss": 1.0570238397273843,
|
| 737 |
+
"eval_mse_loss": 1.0570238397273843,
|
| 738 |
+
"eval_runtime": 100.299,
|
| 739 |
+
"eval_samples_per_second": 279.095,
|
| 740 |
+
"eval_steps_per_second": 4.367,
|
| 741 |
+
"step": 17408
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.8158514618262436,
|
| 745 |
+
"grad_norm": 0.22125214338302612,
|
| 746 |
+
"learning_rate": 3.604120062842402e-05,
|
| 747 |
+
"loss": 1.1033,
|
| 748 |
+
"step": 17664
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.8276753960556095,
|
| 752 |
+
"grad_norm": 0.2175501137971878,
|
| 753 |
+
"learning_rate": 3.168926234667766e-05,
|
| 754 |
+
"loss": 1.1094,
|
| 755 |
+
"step": 17920
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.8394993302849753,
|
| 759 |
+
"grad_norm": 0.2011047899723053,
|
| 760 |
+
"learning_rate": 2.759463132282547e-05,
|
| 761 |
+
"loss": 1.1108,
|
| 762 |
+
"step": 18176
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.8513232645143411,
|
| 766 |
+
"grad_norm": 0.2260669618844986,
|
| 767 |
+
"learning_rate": 2.3763567277996935e-05,
|
| 768 |
+
"loss": 1.1152,
|
| 769 |
+
"step": 18432
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.8513232645143411,
|
| 773 |
+
"eval_loss": 1.0761699030116267,
|
| 774 |
+
"eval_mse_loss": 1.0761699030116267,
|
| 775 |
+
"step": 18432
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.8513232645143411,
|
| 779 |
+
"eval_loss": 1.0761699030116267,
|
| 780 |
+
"eval_mse_loss": 1.0761699030116267,
|
| 781 |
+
"eval_runtime": 99.8777,
|
| 782 |
+
"eval_samples_per_second": 280.273,
|
| 783 |
+
"eval_steps_per_second": 4.385,
|
| 784 |
+
"step": 18432
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.8631471987437069,
|
| 788 |
+
"grad_norm": 0.18276292085647583,
|
| 789 |
+
"learning_rate": 2.0201927001829836e-05,
|
| 790 |
+
"loss": 1.1203,
|
| 791 |
+
"step": 18688
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.8749711329730728,
|
| 795 |
+
"grad_norm": 0.172455832362175,
|
| 796 |
+
"learning_rate": 1.6915155398825423e-05,
|
| 797 |
+
"loss": 1.124,
|
| 798 |
+
"step": 18944
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.8867950672024387,
|
| 802 |
+
"grad_norm": 0.20908404886722565,
|
| 803 |
+
"learning_rate": 1.3919472160342173e-05,
|
| 804 |
+
"loss": 1.1311,
|
| 805 |
+
"step": 19200
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.8986190014318045,
|
| 809 |
+
"grad_norm": 0.19443683326244354,
|
| 810 |
+
"learning_rate": 1.1195964427203121e-05,
|
| 811 |
+
"loss": 1.1341,
|
| 812 |
+
"step": 19456
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.8986190014318045,
|
| 816 |
+
"eval_loss": 1.0952530190280583,
|
| 817 |
+
"eval_mse_loss": 1.0952530190280583,
|
| 818 |
+
"step": 19456
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.8986190014318045,
|
| 822 |
+
"eval_loss": 1.0952530190280583,
|
| 823 |
+
"eval_mse_loss": 1.0952530190280583,
|
| 824 |
+
"eval_runtime": 100.0076,
|
| 825 |
+
"eval_samples_per_second": 279.909,
|
| 826 |
+
"eval_steps_per_second": 4.38,
|
| 827 |
+
"step": 19456
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.9104429356611704,
|
| 831 |
+
"grad_norm": 0.16602899134159088,
|
| 832 |
+
"learning_rate": 8.761093351177674e-06,
|
| 833 |
+
"loss": 1.1367,
|
| 834 |
+
"step": 19712
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.9222668698905362,
|
| 838 |
+
"grad_norm": 0.1926073431968689,
|
| 839 |
+
"learning_rate": 6.618581273505786e-06,
|
| 840 |
+
"loss": 1.145,
|
| 841 |
+
"step": 19968
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.9340908041199021,
|
| 845 |
+
"grad_norm": 0.19851690530776978,
|
| 846 |
+
"learning_rate": 4.771703587756516e-06,
|
| 847 |
+
"loss": 1.1507,
|
| 848 |
+
"step": 20224
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.945914738349268,
|
| 852 |
+
"grad_norm": 0.19018347561359406,
|
| 853 |
+
"learning_rate": 3.223283732526894e-06,
|
| 854 |
+
"loss": 1.1569,
|
| 855 |
+
"step": 20480
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.945914738349268,
|
| 859 |
+
"eval_loss": 1.1172848334323326,
|
| 860 |
+
"eval_mse_loss": 1.1172848334323326,
|
| 861 |
+
"step": 20480
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.945914738349268,
|
| 865 |
+
"eval_loss": 1.1172848334323326,
|
| 866 |
+
"eval_mse_loss": 1.1172848334323326,
|
| 867 |
+
"eval_runtime": 101.775,
|
| 868 |
+
"eval_samples_per_second": 275.048,
|
| 869 |
+
"eval_steps_per_second": 4.304,
|
| 870 |
+
"step": 20480
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.9577386725786338,
|
| 874 |
+
"grad_norm": 0.1803227663040161,
|
| 875 |
+
"learning_rate": 1.9756888750729786e-06,
|
| 876 |
+
"loss": 1.1608,
|
| 877 |
+
"step": 20736
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.9695626068079997,
|
| 881 |
+
"grad_norm": 0.1926874816417694,
|
| 882 |
+
"learning_rate": 1.0308262924717538e-06,
|
| 883 |
+
"loss": 1.1687,
|
| 884 |
+
"step": 20992
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.9813865410373654,
|
| 888 |
+
"grad_norm": 0.21967464685440063,
|
| 889 |
+
"learning_rate": 3.90140455846133e-07,
|
| 890 |
+
"loss": 1.175,
|
| 891 |
+
"step": 21248
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.9932104752667313,
|
| 895 |
+
"grad_norm": 0.16599184274673462,
|
| 896 |
+
"learning_rate": 5.532698894212818e-08,
|
| 897 |
+
"loss": 1.1762,
|
| 898 |
+
"step": 21504
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.9932104752667313,
|
| 902 |
+
"eval_loss": 1.1381378846081425,
|
| 903 |
+
"eval_mse_loss": 1.1381378846081425,
|
| 904 |
+
"step": 21504
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.9932104752667313,
|
| 908 |
+
"eval_loss": 1.1381378846081425,
|
| 909 |
+
"eval_mse_loss": 1.1381378846081425,
|
| 910 |
+
"eval_runtime": 99.4896,
|
| 911 |
+
"eval_samples_per_second": 281.366,
|
| 912 |
+
"eval_steps_per_second": 4.402,
|
| 913 |
+
"step": 21504
|
| 914 |
+
}
|
| 915 |
+
],
|
| 916 |
+
"logging_steps": 256,
|
| 917 |
+
"max_steps": 21651,
|
| 918 |
+
"num_input_tokens_seen": 0,
|
| 919 |
+
"num_train_epochs": 1,
|
| 920 |
+
"save_steps": 1024,
|
| 921 |
+
"stateful_callbacks": {
|
| 922 |
+
"TrainerControl": {
|
| 923 |
+
"args": {
|
| 924 |
+
"should_epoch_stop": false,
|
| 925 |
+
"should_evaluate": false,
|
| 926 |
+
"should_log": false,
|
| 927 |
+
"should_save": true,
|
| 928 |
+
"should_training_stop": true
|
| 929 |
+
},
|
| 930 |
+
"attributes": {}
|
| 931 |
+
}
|
| 932 |
+
},
|
| 933 |
+
"total_flos": 0.0,
|
| 934 |
+
"train_batch_size": 64,
|
| 935 |
+
"trial_name": null,
|
| 936 |
+
"trial_params": null
|
| 937 |
+
}
|
checkpoints/checkpoint-21651/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c9b601f2d9cc5910b4d51f85ab22a2e835b407c81b98749f8408466eb47ba16
|
| 3 |
+
size 5777
|