Training in progress, step 5400, checkpoint
Browse files- last-checkpoint/adapter_config.json +2 -2
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +671 -5
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
|
@@ -32,9 +32,9 @@
|
|
| 32 |
"revision": null,
|
| 33 |
"target_modules": [
|
| 34 |
"q_proj",
|
| 35 |
-
"v_proj",
|
| 36 |
"o_proj",
|
| 37 |
-
"k_proj"
|
|
|
|
| 38 |
],
|
| 39 |
"target_parameters": null,
|
| 40 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 32 |
"revision": null,
|
| 33 |
"target_modules": [
|
| 34 |
"q_proj",
|
|
|
|
| 35 |
"o_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"v_proj"
|
| 38 |
],
|
| 39 |
"target_parameters": null,
|
| 40 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14764744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c2b324b8049a18ce1ba034f6aba65985584aa14901fa58e73e8ab119745c91
|
| 3 |
size 14764744
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29614667
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d5dbf3ccb5eae5ac9fbedaf3a3bf948c0bd9f0e56e9fa24be21b44b23bf9cb
|
| 3 |
size 29614667
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcdb3748172857f29588339ceb5799f4474929a2fc74897129d647054ac61d53
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edff8728f15b32954602ef9d3cf6e0a55beee203f9b419667f25948eb333f5b0
|
| 3 |
size 14917
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8053fa83978164af3b1105d8792ddd5aaa5fa308eacd91789cad36b689c1f7e5
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1dc2197e9ad250585b3ac3735f65e4c4e30b977a4b11f1897913f7d241839d3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -5336,12 +5336,678 @@
|
|
| 5336 |
"eval_samples_per_second": 5.161,
|
| 5337 |
"eval_steps_per_second": 1.291,
|
| 5338 |
"step": 4800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5339 |
}
|
| 5340 |
],
|
| 5341 |
"logging_steps": 10,
|
| 5342 |
-
"max_steps":
|
| 5343 |
"num_input_tokens_seen": 0,
|
| 5344 |
-
"num_train_epochs":
|
| 5345 |
"save_steps": 200,
|
| 5346 |
"stateful_callbacks": {
|
| 5347 |
"TrainerControl": {
|
|
@@ -5355,7 +6021,7 @@
|
|
| 5355 |
"attributes": {}
|
| 5356 |
}
|
| 5357 |
},
|
| 5358 |
-
"total_flos":
|
| 5359 |
"train_batch_size": 2,
|
| 5360 |
"trial_name": null,
|
| 5361 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.406642787365679,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 5400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5336 |
"eval_samples_per_second": 5.161,
|
| 5337 |
"eval_steps_per_second": 1.291,
|
| 5338 |
"step": 4800
|
| 5339 |
+
},
|
| 5340 |
+
{
|
| 5341 |
+
"entropy": 0.9813777908682824,
|
| 5342 |
+
"epoch": 1.252946922826441,
|
| 5343 |
+
"grad_norm": 0.44488945603370667,
|
| 5344 |
+
"learning_rate": 7.473300338629852e-06,
|
| 5345 |
+
"loss": 0.9760551452636719,
|
| 5346 |
+
"mean_token_accuracy": 0.7828159511089325,
|
| 5347 |
+
"num_tokens": 129388.0,
|
| 5348 |
+
"step": 4810
|
| 5349 |
+
},
|
| 5350 |
+
{
|
| 5351 |
+
"entropy": 1.028295949101448,
|
| 5352 |
+
"epoch": 1.2555519374796482,
|
| 5353 |
+
"grad_norm": 0.476211279630661,
|
| 5354 |
+
"learning_rate": 7.447251888512634e-06,
|
| 5355 |
+
"loss": 1.026865005493164,
|
| 5356 |
+
"mean_token_accuracy": 0.7739313766360283,
|
| 5357 |
+
"num_tokens": 256578.0,
|
| 5358 |
+
"step": 4820
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"entropy": 0.993380619585514,
|
| 5362 |
+
"epoch": 1.2581569521328557,
|
| 5363 |
+
"grad_norm": 0.5022156834602356,
|
| 5364 |
+
"learning_rate": 7.4212034383954155e-06,
|
| 5365 |
+
"loss": 0.9900455474853516,
|
| 5366 |
+
"mean_token_accuracy": 0.7809839487075806,
|
| 5367 |
+
"num_tokens": 379760.0,
|
| 5368 |
+
"step": 4830
|
| 5369 |
+
},
|
| 5370 |
+
{
|
| 5371 |
+
"entropy": 0.9588794216513634,
|
| 5372 |
+
"epoch": 1.2607619667860632,
|
| 5373 |
+
"grad_norm": 0.43847885727882385,
|
| 5374 |
+
"learning_rate": 7.395154988278198e-06,
|
| 5375 |
+
"loss": 0.9578507423400879,
|
| 5376 |
+
"mean_token_accuracy": 0.7875250384211541,
|
| 5377 |
+
"num_tokens": 506218.0,
|
| 5378 |
+
"step": 4840
|
| 5379 |
+
},
|
| 5380 |
+
{
|
| 5381 |
+
"entropy": 0.981762844324112,
|
| 5382 |
+
"epoch": 1.2633669814392707,
|
| 5383 |
+
"grad_norm": 0.44927820563316345,
|
| 5384 |
+
"learning_rate": 7.36910653816098e-06,
|
| 5385 |
+
"loss": 0.9703155517578125,
|
| 5386 |
+
"mean_token_accuracy": 0.7809026747941971,
|
| 5387 |
+
"num_tokens": 630994.0,
|
| 5388 |
+
"step": 4850
|
| 5389 |
+
},
|
| 5390 |
+
{
|
| 5391 |
+
"entropy": 0.9776830449700356,
|
| 5392 |
+
"epoch": 1.265971996092478,
|
| 5393 |
+
"grad_norm": 0.4348759055137634,
|
| 5394 |
+
"learning_rate": 7.343058088043762e-06,
|
| 5395 |
+
"loss": 0.9691827774047852,
|
| 5396 |
+
"mean_token_accuracy": 0.7856391072273254,
|
| 5397 |
+
"num_tokens": 757625.0,
|
| 5398 |
+
"step": 4860
|
| 5399 |
+
},
|
| 5400 |
+
{
|
| 5401 |
+
"entropy": 0.9467781752347946,
|
| 5402 |
+
"epoch": 1.2685770107456855,
|
| 5403 |
+
"grad_norm": 0.4643247127532959,
|
| 5404 |
+
"learning_rate": 7.3170096379265445e-06,
|
| 5405 |
+
"loss": 0.9435815811157227,
|
| 5406 |
+
"mean_token_accuracy": 0.7907302647829055,
|
| 5407 |
+
"num_tokens": 881836.0,
|
| 5408 |
+
"step": 4870
|
| 5409 |
+
},
|
| 5410 |
+
{
|
| 5411 |
+
"entropy": 0.9590273395180702,
|
| 5412 |
+
"epoch": 1.2711820253988928,
|
| 5413 |
+
"grad_norm": 0.45526987314224243,
|
| 5414 |
+
"learning_rate": 7.290961187809326e-06,
|
| 5415 |
+
"loss": 0.9674400329589844,
|
| 5416 |
+
"mean_token_accuracy": 0.785734324157238,
|
| 5417 |
+
"num_tokens": 1011144.0,
|
| 5418 |
+
"step": 4880
|
| 5419 |
+
},
|
| 5420 |
+
{
|
| 5421 |
+
"entropy": 1.017872877418995,
|
| 5422 |
+
"epoch": 1.2737870400521003,
|
| 5423 |
+
"grad_norm": 0.42657098174095154,
|
| 5424 |
+
"learning_rate": 7.264912737692108e-06,
|
| 5425 |
+
"loss": 1.0152156829833985,
|
| 5426 |
+
"mean_token_accuracy": 0.7740847021341324,
|
| 5427 |
+
"num_tokens": 1136047.0,
|
| 5428 |
+
"step": 4890
|
| 5429 |
+
},
|
| 5430 |
+
{
|
| 5431 |
+
"entropy": 0.993815653026104,
|
| 5432 |
+
"epoch": 1.2763920547053078,
|
| 5433 |
+
"grad_norm": 0.4295169711112976,
|
| 5434 |
+
"learning_rate": 7.23886428757489e-06,
|
| 5435 |
+
"loss": 0.9871231079101562,
|
| 5436 |
+
"mean_token_accuracy": 0.7813043370842934,
|
| 5437 |
+
"num_tokens": 1258878.0,
|
| 5438 |
+
"step": 4900
|
| 5439 |
+
},
|
| 5440 |
+
{
|
| 5441 |
+
"epoch": 1.2763920547053078,
|
| 5442 |
+
"eval_entropy": 0.9970914693472669,
|
| 5443 |
+
"eval_loss": 0.9884027242660522,
|
| 5444 |
+
"eval_mean_token_accuracy": 0.7808390200208133,
|
| 5445 |
+
"eval_num_tokens": 1258878.0,
|
| 5446 |
+
"eval_runtime": 1248.5811,
|
| 5447 |
+
"eval_samples_per_second": 5.451,
|
| 5448 |
+
"eval_steps_per_second": 1.363,
|
| 5449 |
+
"step": 4900
|
| 5450 |
+
},
|
| 5451 |
+
{
|
| 5452 |
+
"entropy": 1.0345384523272514,
|
| 5453 |
+
"epoch": 1.278997069358515,
|
| 5454 |
+
"grad_norm": 0.46928712725639343,
|
| 5455 |
+
"learning_rate": 7.212815837457672e-06,
|
| 5456 |
+
"loss": 1.0300195693969727,
|
| 5457 |
+
"mean_token_accuracy": 0.771189559996128,
|
| 5458 |
+
"num_tokens": 1386649.0,
|
| 5459 |
+
"step": 4910
|
| 5460 |
+
},
|
| 5461 |
+
{
|
| 5462 |
+
"entropy": 1.0029998540878295,
|
| 5463 |
+
"epoch": 1.2816020840117226,
|
| 5464 |
+
"grad_norm": 0.48189452290534973,
|
| 5465 |
+
"learning_rate": 7.186767387340454e-06,
|
| 5466 |
+
"loss": 0.9906700134277344,
|
| 5467 |
+
"mean_token_accuracy": 0.7785976707935334,
|
| 5468 |
+
"num_tokens": 1512338.0,
|
| 5469 |
+
"step": 4920
|
| 5470 |
+
},
|
| 5471 |
+
{
|
| 5472 |
+
"entropy": 1.0033065855503083,
|
| 5473 |
+
"epoch": 1.2842070986649299,
|
| 5474 |
+
"grad_norm": 0.4588858187198639,
|
| 5475 |
+
"learning_rate": 7.160718937223236e-06,
|
| 5476 |
+
"loss": 0.9927248001098633,
|
| 5477 |
+
"mean_token_accuracy": 0.7797123953700066,
|
| 5478 |
+
"num_tokens": 1642624.0,
|
| 5479 |
+
"step": 4930
|
| 5480 |
+
},
|
| 5481 |
+
{
|
| 5482 |
+
"entropy": 0.9549823224544525,
|
| 5483 |
+
"epoch": 1.2868121133181374,
|
| 5484 |
+
"grad_norm": 0.43219390511512756,
|
| 5485 |
+
"learning_rate": 7.134670487106018e-06,
|
| 5486 |
+
"loss": 0.9539813041687012,
|
| 5487 |
+
"mean_token_accuracy": 0.7869110450148582,
|
| 5488 |
+
"num_tokens": 1771847.0,
|
| 5489 |
+
"step": 4940
|
| 5490 |
+
},
|
| 5491 |
+
{
|
| 5492 |
+
"entropy": 1.0237484708428384,
|
| 5493 |
+
"epoch": 1.289417127971345,
|
| 5494 |
+
"grad_norm": 0.4907780885696411,
|
| 5495 |
+
"learning_rate": 7.108622036988799e-06,
|
| 5496 |
+
"loss": 1.0278969764709474,
|
| 5497 |
+
"mean_token_accuracy": 0.7715816020965576,
|
| 5498 |
+
"num_tokens": 1900902.0,
|
| 5499 |
+
"step": 4950
|
| 5500 |
+
},
|
| 5501 |
+
{
|
| 5502 |
+
"entropy": 1.006957694888115,
|
| 5503 |
+
"epoch": 1.2920221426245524,
|
| 5504 |
+
"grad_norm": 0.4545274078845978,
|
| 5505 |
+
"learning_rate": 7.082573586871582e-06,
|
| 5506 |
+
"loss": 1.0091020584106445,
|
| 5507 |
+
"mean_token_accuracy": 0.7763800770044327,
|
| 5508 |
+
"num_tokens": 2031777.0,
|
| 5509 |
+
"step": 4960
|
| 5510 |
+
},
|
| 5511 |
+
{
|
| 5512 |
+
"entropy": 0.9983339875936508,
|
| 5513 |
+
"epoch": 1.2946271572777597,
|
| 5514 |
+
"grad_norm": 0.4333556592464447,
|
| 5515 |
+
"learning_rate": 7.056525136754364e-06,
|
| 5516 |
+
"loss": 0.984560203552246,
|
| 5517 |
+
"mean_token_accuracy": 0.7822976499795914,
|
| 5518 |
+
"num_tokens": 2156527.0,
|
| 5519 |
+
"step": 4970
|
| 5520 |
+
},
|
| 5521 |
+
{
|
| 5522 |
+
"entropy": 0.9773911476135254,
|
| 5523 |
+
"epoch": 1.2972321719309672,
|
| 5524 |
+
"grad_norm": 0.4380306303501129,
|
| 5525 |
+
"learning_rate": 7.030476686637145e-06,
|
| 5526 |
+
"loss": 0.9723411560058594,
|
| 5527 |
+
"mean_token_accuracy": 0.7831587105989456,
|
| 5528 |
+
"num_tokens": 2280664.0,
|
| 5529 |
+
"step": 4980
|
| 5530 |
+
},
|
| 5531 |
+
{
|
| 5532 |
+
"entropy": 1.0176811680197715,
|
| 5533 |
+
"epoch": 1.2998371865841745,
|
| 5534 |
+
"grad_norm": 0.49647819995880127,
|
| 5535 |
+
"learning_rate": 7.004428236519928e-06,
|
| 5536 |
+
"loss": 1.0118232727050782,
|
| 5537 |
+
"mean_token_accuracy": 0.7755638837814331,
|
| 5538 |
+
"num_tokens": 2408726.0,
|
| 5539 |
+
"step": 4990
|
| 5540 |
+
},
|
| 5541 |
+
{
|
| 5542 |
+
"entropy": 1.003194873034954,
|
| 5543 |
+
"epoch": 1.302442201237382,
|
| 5544 |
+
"grad_norm": 0.4423670470714569,
|
| 5545 |
+
"learning_rate": 6.978379786402709e-06,
|
| 5546 |
+
"loss": 0.9979192733764648,
|
| 5547 |
+
"mean_token_accuracy": 0.7790161743760109,
|
| 5548 |
+
"num_tokens": 2538321.0,
|
| 5549 |
+
"step": 5000
|
| 5550 |
+
},
|
| 5551 |
+
{
|
| 5552 |
+
"epoch": 1.302442201237382,
|
| 5553 |
+
"eval_entropy": 0.9890262984991354,
|
| 5554 |
+
"eval_loss": 0.9879328608512878,
|
| 5555 |
+
"eval_mean_token_accuracy": 0.7809134237774671,
|
| 5556 |
+
"eval_num_tokens": 2538321.0,
|
| 5557 |
+
"eval_runtime": 1248.3546,
|
| 5558 |
+
"eval_samples_per_second": 5.452,
|
| 5559 |
+
"eval_steps_per_second": 1.363,
|
| 5560 |
+
"step": 5000
|
| 5561 |
+
},
|
| 5562 |
+
{
|
| 5563 |
+
"entropy": 0.9911179274320603,
|
| 5564 |
+
"epoch": 1.3050472158905895,
|
| 5565 |
+
"grad_norm": 0.4474965035915375,
|
| 5566 |
+
"learning_rate": 6.952331336285491e-06,
|
| 5567 |
+
"loss": 0.9846304893493653,
|
| 5568 |
+
"mean_token_accuracy": 0.7800104588270187,
|
| 5569 |
+
"num_tokens": 2664423.0,
|
| 5570 |
+
"step": 5010
|
| 5571 |
+
},
|
| 5572 |
+
{
|
| 5573 |
+
"entropy": 0.9809451669454574,
|
| 5574 |
+
"epoch": 1.3076522305437968,
|
| 5575 |
+
"grad_norm": 0.4665301442146301,
|
| 5576 |
+
"learning_rate": 6.926282886168274e-06,
|
| 5577 |
+
"loss": 0.9809820175170898,
|
| 5578 |
+
"mean_token_accuracy": 0.7841726258397103,
|
| 5579 |
+
"num_tokens": 2790315.0,
|
| 5580 |
+
"step": 5020
|
| 5581 |
+
},
|
| 5582 |
+
{
|
| 5583 |
+
"entropy": 0.9852373987436295,
|
| 5584 |
+
"epoch": 1.3102572451970043,
|
| 5585 |
+
"grad_norm": 0.429098516702652,
|
| 5586 |
+
"learning_rate": 6.900234436051055e-06,
|
| 5587 |
+
"loss": 0.9816387176513672,
|
| 5588 |
+
"mean_token_accuracy": 0.7819439515471458,
|
| 5589 |
+
"num_tokens": 2915995.0,
|
| 5590 |
+
"step": 5030
|
| 5591 |
+
},
|
| 5592 |
+
{
|
| 5593 |
+
"entropy": 0.986951345205307,
|
| 5594 |
+
"epoch": 1.3128622598502115,
|
| 5595 |
+
"grad_norm": 0.45305219292640686,
|
| 5596 |
+
"learning_rate": 6.874185985933837e-06,
|
| 5597 |
+
"loss": 0.9891517639160157,
|
| 5598 |
+
"mean_token_accuracy": 0.780052900314331,
|
| 5599 |
+
"num_tokens": 3041830.0,
|
| 5600 |
+
"step": 5040
|
| 5601 |
+
},
|
| 5602 |
+
{
|
| 5603 |
+
"entropy": 1.0265516340732574,
|
| 5604 |
+
"epoch": 1.315467274503419,
|
| 5605 |
+
"grad_norm": 0.4666403532028198,
|
| 5606 |
+
"learning_rate": 6.848137535816619e-06,
|
| 5607 |
+
"loss": 1.0243612289428712,
|
| 5608 |
+
"mean_token_accuracy": 0.7726057410240174,
|
| 5609 |
+
"num_tokens": 3167296.0,
|
| 5610 |
+
"step": 5050
|
| 5611 |
+
},
|
| 5612 |
+
{
|
| 5613 |
+
"entropy": 1.0306162551045417,
|
| 5614 |
+
"epoch": 1.3180722891566266,
|
| 5615 |
+
"grad_norm": 0.39735814929008484,
|
| 5616 |
+
"learning_rate": 6.8220890856994014e-06,
|
| 5617 |
+
"loss": 1.0236353874206543,
|
| 5618 |
+
"mean_token_accuracy": 0.7734616458415985,
|
| 5619 |
+
"num_tokens": 3292887.0,
|
| 5620 |
+
"step": 5060
|
| 5621 |
+
},
|
| 5622 |
+
{
|
| 5623 |
+
"entropy": 1.0042320653796195,
|
| 5624 |
+
"epoch": 1.320677303809834,
|
| 5625 |
+
"grad_norm": 0.39348119497299194,
|
| 5626 |
+
"learning_rate": 6.796040635582184e-06,
|
| 5627 |
+
"loss": 1.0001495361328125,
|
| 5628 |
+
"mean_token_accuracy": 0.7790237024426461,
|
| 5629 |
+
"num_tokens": 3418112.0,
|
| 5630 |
+
"step": 5070
|
| 5631 |
+
},
|
| 5632 |
+
{
|
| 5633 |
+
"entropy": 1.0145965054631234,
|
| 5634 |
+
"epoch": 1.3232823184630413,
|
| 5635 |
+
"grad_norm": 0.4478921592235565,
|
| 5636 |
+
"learning_rate": 6.7699921854649655e-06,
|
| 5637 |
+
"loss": 1.0137309074401855,
|
| 5638 |
+
"mean_token_accuracy": 0.7771003857254982,
|
| 5639 |
+
"num_tokens": 3548473.0,
|
| 5640 |
+
"step": 5080
|
| 5641 |
+
},
|
| 5642 |
+
{
|
| 5643 |
+
"entropy": 1.0103399023413657,
|
| 5644 |
+
"epoch": 1.3258873331162488,
|
| 5645 |
+
"grad_norm": 0.5050984621047974,
|
| 5646 |
+
"learning_rate": 6.7439437353477475e-06,
|
| 5647 |
+
"loss": 0.999553108215332,
|
| 5648 |
+
"mean_token_accuracy": 0.7785449594259262,
|
| 5649 |
+
"num_tokens": 3673127.0,
|
| 5650 |
+
"step": 5090
|
| 5651 |
+
},
|
| 5652 |
+
{
|
| 5653 |
+
"entropy": 0.966312225162983,
|
| 5654 |
+
"epoch": 1.3284923477694561,
|
| 5655 |
+
"grad_norm": 0.43490949273109436,
|
| 5656 |
+
"learning_rate": 6.717895285230529e-06,
|
| 5657 |
+
"loss": 0.9707491874694825,
|
| 5658 |
+
"mean_token_accuracy": 0.7834598645567894,
|
| 5659 |
+
"num_tokens": 3802026.0,
|
| 5660 |
+
"step": 5100
|
| 5661 |
+
},
|
| 5662 |
+
{
|
| 5663 |
+
"epoch": 1.3284923477694561,
|
| 5664 |
+
"eval_entropy": 0.9884775571971607,
|
| 5665 |
+
"eval_loss": 0.9877337217330933,
|
| 5666 |
+
"eval_mean_token_accuracy": 0.7809631075057805,
|
| 5667 |
+
"eval_num_tokens": 3802026.0,
|
| 5668 |
+
"eval_runtime": 1249.8046,
|
| 5669 |
+
"eval_samples_per_second": 5.446,
|
| 5670 |
+
"eval_steps_per_second": 1.362,
|
| 5671 |
+
"step": 5100
|
| 5672 |
+
},
|
| 5673 |
+
{
|
| 5674 |
+
"entropy": 0.9976687163114548,
|
| 5675 |
+
"epoch": 1.3310973624226636,
|
| 5676 |
+
"grad_norm": 0.43964383006095886,
|
| 5677 |
+
"learning_rate": 6.691846835113312e-06,
|
| 5678 |
+
"loss": 0.9837272644042969,
|
| 5679 |
+
"mean_token_accuracy": 0.7808806389570236,
|
| 5680 |
+
"num_tokens": 3930388.0,
|
| 5681 |
+
"step": 5110
|
| 5682 |
+
},
|
| 5683 |
+
{
|
| 5684 |
+
"entropy": 0.983721150457859,
|
| 5685 |
+
"epoch": 1.3337023770758711,
|
| 5686 |
+
"grad_norm": 0.46595776081085205,
|
| 5687 |
+
"learning_rate": 6.665798384996093e-06,
|
| 5688 |
+
"loss": 0.9791852951049804,
|
| 5689 |
+
"mean_token_accuracy": 0.7797340914607048,
|
| 5690 |
+
"num_tokens": 4057438.0,
|
| 5691 |
+
"step": 5120
|
| 5692 |
+
},
|
| 5693 |
+
{
|
| 5694 |
+
"entropy": 1.0189708486199378,
|
| 5695 |
+
"epoch": 1.3363073917290784,
|
| 5696 |
+
"grad_norm": 0.4384433329105377,
|
| 5697 |
+
"learning_rate": 6.639749934878875e-06,
|
| 5698 |
+
"loss": 1.0155632019042968,
|
| 5699 |
+
"mean_token_accuracy": 0.7752848476171493,
|
| 5700 |
+
"num_tokens": 4184226.0,
|
| 5701 |
+
"step": 5130
|
| 5702 |
+
},
|
| 5703 |
+
{
|
| 5704 |
+
"entropy": 0.9738220989704132,
|
| 5705 |
+
"epoch": 1.338912406382286,
|
| 5706 |
+
"grad_norm": 0.4892994463443756,
|
| 5707 |
+
"learning_rate": 6.613701484761658e-06,
|
| 5708 |
+
"loss": 0.9773561477661132,
|
| 5709 |
+
"mean_token_accuracy": 0.7810323163866997,
|
| 5710 |
+
"num_tokens": 4315468.0,
|
| 5711 |
+
"step": 5140
|
| 5712 |
+
},
|
| 5713 |
+
{
|
| 5714 |
+
"entropy": 0.9959368094801903,
|
| 5715 |
+
"epoch": 1.3415174210354932,
|
| 5716 |
+
"grad_norm": 0.4051533043384552,
|
| 5717 |
+
"learning_rate": 6.587653034644439e-06,
|
| 5718 |
+
"loss": 0.9895273208618164,
|
| 5719 |
+
"mean_token_accuracy": 0.7815038353204727,
|
| 5720 |
+
"num_tokens": 4439960.0,
|
| 5721 |
+
"step": 5150
|
| 5722 |
+
},
|
| 5723 |
+
{
|
| 5724 |
+
"entropy": 0.9800890773534775,
|
| 5725 |
+
"epoch": 1.3441224356887007,
|
| 5726 |
+
"grad_norm": 0.4586341679096222,
|
| 5727 |
+
"learning_rate": 6.561604584527222e-06,
|
| 5728 |
+
"loss": 0.9737453460693359,
|
| 5729 |
+
"mean_token_accuracy": 0.7814203977584839,
|
| 5730 |
+
"num_tokens": 4566056.0,
|
| 5731 |
+
"step": 5160
|
| 5732 |
+
},
|
| 5733 |
+
{
|
| 5734 |
+
"entropy": 1.0000663980841638,
|
| 5735 |
+
"epoch": 1.3467274503419082,
|
| 5736 |
+
"grad_norm": 0.4102465510368347,
|
| 5737 |
+
"learning_rate": 6.535556134410003e-06,
|
| 5738 |
+
"loss": 0.9939519882202148,
|
| 5739 |
+
"mean_token_accuracy": 0.7790467858314514,
|
| 5740 |
+
"num_tokens": 4694925.0,
|
| 5741 |
+
"step": 5170
|
| 5742 |
+
},
|
| 5743 |
+
{
|
| 5744 |
+
"entropy": 1.0039643123745918,
|
| 5745 |
+
"epoch": 1.3493324649951157,
|
| 5746 |
+
"grad_norm": 0.4231637418270111,
|
| 5747 |
+
"learning_rate": 6.509507684292785e-06,
|
| 5748 |
+
"loss": 1.001540756225586,
|
| 5749 |
+
"mean_token_accuracy": 0.7798496216535569,
|
| 5750 |
+
"num_tokens": 4817681.0,
|
| 5751 |
+
"step": 5180
|
| 5752 |
+
},
|
| 5753 |
+
{
|
| 5754 |
+
"entropy": 0.9824537605047226,
|
| 5755 |
+
"epoch": 1.351937479648323,
|
| 5756 |
+
"grad_norm": 0.4193444550037384,
|
| 5757 |
+
"learning_rate": 6.483459234175568e-06,
|
| 5758 |
+
"loss": 0.9902861595153809,
|
| 5759 |
+
"mean_token_accuracy": 0.7809780746698379,
|
| 5760 |
+
"num_tokens": 4946004.0,
|
| 5761 |
+
"step": 5190
|
| 5762 |
+
},
|
| 5763 |
+
{
|
| 5764 |
+
"entropy": 0.9934640824794769,
|
| 5765 |
+
"epoch": 1.3545424943015305,
|
| 5766 |
+
"grad_norm": 0.5171741843223572,
|
| 5767 |
+
"learning_rate": 6.457410784058349e-06,
|
| 5768 |
+
"loss": 0.9897693634033203,
|
| 5769 |
+
"mean_token_accuracy": 0.7789523780345917,
|
| 5770 |
+
"num_tokens": 5071552.0,
|
| 5771 |
+
"step": 5200
|
| 5772 |
+
},
|
| 5773 |
+
{
|
| 5774 |
+
"epoch": 1.3545424943015305,
|
| 5775 |
+
"eval_entropy": 0.9874165067941686,
|
| 5776 |
+
"eval_loss": 0.9873093962669373,
|
| 5777 |
+
"eval_mean_token_accuracy": 0.7809983336757409,
|
| 5778 |
+
"eval_num_tokens": 5071552.0,
|
| 5779 |
+
"eval_runtime": 1248.5888,
|
| 5780 |
+
"eval_samples_per_second": 5.451,
|
| 5781 |
+
"eval_steps_per_second": 1.363,
|
| 5782 |
+
"step": 5200
|
| 5783 |
+
},
|
| 5784 |
+
{
|
| 5785 |
+
"entropy": 0.9975464969873429,
|
| 5786 |
+
"epoch": 1.3571475089547378,
|
| 5787 |
+
"grad_norm": 0.43779075145721436,
|
| 5788 |
+
"learning_rate": 6.431362333941131e-06,
|
| 5789 |
+
"loss": 0.9847593307495117,
|
| 5790 |
+
"mean_token_accuracy": 0.7821353122591972,
|
| 5791 |
+
"num_tokens": 5199409.0,
|
| 5792 |
+
"step": 5210
|
| 5793 |
+
},
|
| 5794 |
+
{
|
| 5795 |
+
"entropy": 0.9890801250934601,
|
| 5796 |
+
"epoch": 1.3597525236079453,
|
| 5797 |
+
"grad_norm": 0.46792900562286377,
|
| 5798 |
+
"learning_rate": 6.405313883823912e-06,
|
| 5799 |
+
"loss": 0.9886545181274414,
|
| 5800 |
+
"mean_token_accuracy": 0.7808847963809967,
|
| 5801 |
+
"num_tokens": 5327018.0,
|
| 5802 |
+
"step": 5220
|
| 5803 |
+
},
|
| 5804 |
+
{
|
| 5805 |
+
"entropy": 1.0165737330913545,
|
| 5806 |
+
"epoch": 1.3623575382611528,
|
| 5807 |
+
"grad_norm": 0.422018438577652,
|
| 5808 |
+
"learning_rate": 6.379265433706695e-06,
|
| 5809 |
+
"loss": 1.0161245346069336,
|
| 5810 |
+
"mean_token_accuracy": 0.7733713835477829,
|
| 5811 |
+
"num_tokens": 5453326.0,
|
| 5812 |
+
"step": 5230
|
| 5813 |
+
},
|
| 5814 |
+
{
|
| 5815 |
+
"entropy": 0.9966152131557464,
|
| 5816 |
+
"epoch": 1.36496255291436,
|
| 5817 |
+
"grad_norm": 0.46802228689193726,
|
| 5818 |
+
"learning_rate": 6.353216983589477e-06,
|
| 5819 |
+
"loss": 0.9952875137329101,
|
| 5820 |
+
"mean_token_accuracy": 0.7801799476146698,
|
| 5821 |
+
"num_tokens": 5579340.0,
|
| 5822 |
+
"step": 5240
|
| 5823 |
+
},
|
| 5824 |
+
{
|
| 5825 |
+
"entropy": 1.013704551756382,
|
| 5826 |
+
"epoch": 1.3675675675675676,
|
| 5827 |
+
"grad_norm": 0.4642789363861084,
|
| 5828 |
+
"learning_rate": 6.327168533472258e-06,
|
| 5829 |
+
"loss": 1.0044668197631836,
|
| 5830 |
+
"mean_token_accuracy": 0.7750307902693748,
|
| 5831 |
+
"num_tokens": 5704206.0,
|
| 5832 |
+
"step": 5250
|
| 5833 |
+
},
|
| 5834 |
+
{
|
| 5835 |
+
"entropy": 0.9664336591959,
|
| 5836 |
+
"epoch": 1.3701725822207749,
|
| 5837 |
+
"grad_norm": 0.45772185921669006,
|
| 5838 |
+
"learning_rate": 6.301120083355041e-06,
|
| 5839 |
+
"loss": 0.9622204780578614,
|
| 5840 |
+
"mean_token_accuracy": 0.7862247511744499,
|
| 5841 |
+
"num_tokens": 5832067.0,
|
| 5842 |
+
"step": 5260
|
| 5843 |
+
},
|
| 5844 |
+
{
|
| 5845 |
+
"entropy": 0.9767679080367089,
|
| 5846 |
+
"epoch": 1.3727775968739824,
|
| 5847 |
+
"grad_norm": 0.4938032627105713,
|
| 5848 |
+
"learning_rate": 6.2750716332378225e-06,
|
| 5849 |
+
"loss": 0.9772611618041992,
|
| 5850 |
+
"mean_token_accuracy": 0.7834762305021286,
|
| 5851 |
+
"num_tokens": 5956416.0,
|
| 5852 |
+
"step": 5270
|
| 5853 |
+
},
|
| 5854 |
+
{
|
| 5855 |
+
"entropy": 0.997693844139576,
|
| 5856 |
+
"epoch": 1.3753826115271899,
|
| 5857 |
+
"grad_norm": 0.4085782766342163,
|
| 5858 |
+
"learning_rate": 6.249023183120605e-06,
|
| 5859 |
+
"loss": 0.993937873840332,
|
| 5860 |
+
"mean_token_accuracy": 0.7790059551596642,
|
| 5861 |
+
"num_tokens": 6080387.0,
|
| 5862 |
+
"step": 5280
|
| 5863 |
+
},
|
| 5864 |
+
{
|
| 5865 |
+
"entropy": 0.9551204591989517,
|
| 5866 |
+
"epoch": 1.3779876261803974,
|
| 5867 |
+
"grad_norm": 0.47124868631362915,
|
| 5868 |
+
"learning_rate": 6.2229747330033865e-06,
|
| 5869 |
+
"loss": 0.9600910186767578,
|
| 5870 |
+
"mean_token_accuracy": 0.7857999742031098,
|
| 5871 |
+
"num_tokens": 6210495.0,
|
| 5872 |
+
"step": 5290
|
| 5873 |
+
},
|
| 5874 |
+
{
|
| 5875 |
+
"entropy": 0.9895543649792671,
|
| 5876 |
+
"epoch": 1.3805926408336047,
|
| 5877 |
+
"grad_norm": 0.4795711934566498,
|
| 5878 |
+
"learning_rate": 6.196926282886169e-06,
|
| 5879 |
+
"loss": 0.980061149597168,
|
| 5880 |
+
"mean_token_accuracy": 0.7814426705241203,
|
| 5881 |
+
"num_tokens": 6338971.0,
|
| 5882 |
+
"step": 5300
|
| 5883 |
+
},
|
| 5884 |
+
{
|
| 5885 |
+
"epoch": 1.3805926408336047,
|
| 5886 |
+
"eval_entropy": 0.9903583783310532,
|
| 5887 |
+
"eval_loss": 0.9870790839195251,
|
| 5888 |
+
"eval_mean_token_accuracy": 0.781017405095868,
|
| 5889 |
+
"eval_num_tokens": 6338971.0,
|
| 5890 |
+
"eval_runtime": 1249.0996,
|
| 5891 |
+
"eval_samples_per_second": 5.449,
|
| 5892 |
+
"eval_steps_per_second": 1.363,
|
| 5893 |
+
"step": 5300
|
| 5894 |
+
},
|
| 5895 |
+
{
|
| 5896 |
+
"entropy": 1.0024344369769096,
|
| 5897 |
+
"epoch": 1.3831976554868122,
|
| 5898 |
+
"grad_norm": 0.44125476479530334,
|
| 5899 |
+
"learning_rate": 6.1708778327689515e-06,
|
| 5900 |
+
"loss": 1.0059074401855468,
|
| 5901 |
+
"mean_token_accuracy": 0.7774184092879295,
|
| 5902 |
+
"num_tokens": 6465148.0,
|
| 5903 |
+
"step": 5310
|
| 5904 |
+
},
|
| 5905 |
+
{
|
| 5906 |
+
"entropy": 0.9910042881965637,
|
| 5907 |
+
"epoch": 1.3858026701400195,
|
| 5908 |
+
"grad_norm": 0.4707449972629547,
|
| 5909 |
+
"learning_rate": 6.144829382651733e-06,
|
| 5910 |
+
"loss": 0.987660026550293,
|
| 5911 |
+
"mean_token_accuracy": 0.7800036445260048,
|
| 5912 |
+
"num_tokens": 6592528.0,
|
| 5913 |
+
"step": 5320
|
| 5914 |
+
},
|
| 5915 |
+
{
|
| 5916 |
+
"entropy": 0.9776637852191925,
|
| 5917 |
+
"epoch": 1.388407684793227,
|
| 5918 |
+
"grad_norm": 0.40415525436401367,
|
| 5919 |
+
"learning_rate": 6.118780932534515e-06,
|
| 5920 |
+
"loss": 0.9776216506958008,
|
| 5921 |
+
"mean_token_accuracy": 0.7837252721190453,
|
| 5922 |
+
"num_tokens": 6718090.0,
|
| 5923 |
+
"step": 5330
|
| 5924 |
+
},
|
| 5925 |
+
{
|
| 5926 |
+
"entropy": 0.9891742005944252,
|
| 5927 |
+
"epoch": 1.3910126994464345,
|
| 5928 |
+
"grad_norm": 0.4758605659008026,
|
| 5929 |
+
"learning_rate": 6.092732482417296e-06,
|
| 5930 |
+
"loss": 0.9910886764526368,
|
| 5931 |
+
"mean_token_accuracy": 0.7781824618577957,
|
| 5932 |
+
"num_tokens": 6845948.0,
|
| 5933 |
+
"step": 5340
|
| 5934 |
+
},
|
| 5935 |
+
{
|
| 5936 |
+
"entropy": 1.007858295738697,
|
| 5937 |
+
"epoch": 1.3936177140996417,
|
| 5938 |
+
"grad_norm": 0.47813597321510315,
|
| 5939 |
+
"learning_rate": 6.066684032300079e-06,
|
| 5940 |
+
"loss": 1.0086344718933105,
|
| 5941 |
+
"mean_token_accuracy": 0.7754964306950569,
|
| 5942 |
+
"num_tokens": 6973246.0,
|
| 5943 |
+
"step": 5350
|
| 5944 |
+
},
|
| 5945 |
+
{
|
| 5946 |
+
"entropy": 1.0145272225141526,
|
| 5947 |
+
"epoch": 1.3962227287528493,
|
| 5948 |
+
"grad_norm": 0.4583241939544678,
|
| 5949 |
+
"learning_rate": 6.040635582182861e-06,
|
| 5950 |
+
"loss": 1.0088977813720703,
|
| 5951 |
+
"mean_token_accuracy": 0.775096683204174,
|
| 5952 |
+
"num_tokens": 7099698.0,
|
| 5953 |
+
"step": 5360
|
| 5954 |
+
},
|
| 5955 |
+
{
|
| 5956 |
+
"entropy": 1.0434660747647286,
|
| 5957 |
+
"epoch": 1.3988277434060565,
|
| 5958 |
+
"grad_norm": 0.4353461265563965,
|
| 5959 |
+
"learning_rate": 6.014587132065642e-06,
|
| 5960 |
+
"loss": 1.0382314682006837,
|
| 5961 |
+
"mean_token_accuracy": 0.7711483478546143,
|
| 5962 |
+
"num_tokens": 7223734.0,
|
| 5963 |
+
"step": 5370
|
| 5964 |
+
},
|
| 5965 |
+
{
|
| 5966 |
+
"entropy": 0.990787972509861,
|
| 5967 |
+
"epoch": 1.401432758059264,
|
| 5968 |
+
"grad_norm": 0.47876155376434326,
|
| 5969 |
+
"learning_rate": 5.988538681948425e-06,
|
| 5970 |
+
"loss": 0.989743995666504,
|
| 5971 |
+
"mean_token_accuracy": 0.7813950344920159,
|
| 5972 |
+
"num_tokens": 7350371.0,
|
| 5973 |
+
"step": 5380
|
| 5974 |
+
},
|
| 5975 |
+
{
|
| 5976 |
+
"entropy": 1.0080674409866333,
|
| 5977 |
+
"epoch": 1.4040377727124715,
|
| 5978 |
+
"grad_norm": 0.5123191475868225,
|
| 5979 |
+
"learning_rate": 5.962490231831206e-06,
|
| 5980 |
+
"loss": 1.002880859375,
|
| 5981 |
+
"mean_token_accuracy": 0.7779936477541923,
|
| 5982 |
+
"num_tokens": 7477903.0,
|
| 5983 |
+
"step": 5390
|
| 5984 |
+
},
|
| 5985 |
+
{
|
| 5986 |
+
"entropy": 1.0048462897539139,
|
| 5987 |
+
"epoch": 1.406642787365679,
|
| 5988 |
+
"grad_norm": 0.4499814212322235,
|
| 5989 |
+
"learning_rate": 5.936441781713989e-06,
|
| 5990 |
+
"loss": 0.999144458770752,
|
| 5991 |
+
"mean_token_accuracy": 0.7778741553425789,
|
| 5992 |
+
"num_tokens": 7604005.0,
|
| 5993 |
+
"step": 5400
|
| 5994 |
+
},
|
| 5995 |
+
{
|
| 5996 |
+
"epoch": 1.406642787365679,
|
| 5997 |
+
"eval_entropy": 0.9904807468068586,
|
| 5998 |
+
"eval_loss": 0.9868780970573425,
|
| 5999 |
+
"eval_mean_token_accuracy": 0.7810666585290754,
|
| 6000 |
+
"eval_num_tokens": 7604005.0,
|
| 6001 |
+
"eval_runtime": 1248.7827,
|
| 6002 |
+
"eval_samples_per_second": 5.45,
|
| 6003 |
+
"eval_steps_per_second": 1.363,
|
| 6004 |
+
"step": 5400
|
| 6005 |
}
|
| 6006 |
],
|
| 6007 |
"logging_steps": 10,
|
| 6008 |
+
"max_steps": 7678,
|
| 6009 |
"num_input_tokens_seen": 0,
|
| 6010 |
+
"num_train_epochs": 2,
|
| 6011 |
"save_steps": 200,
|
| 6012 |
"stateful_callbacks": {
|
| 6013 |
"TrainerControl": {
|
|
|
|
| 6021 |
"attributes": {}
|
| 6022 |
}
|
| 6023 |
},
|
| 6024 |
+
"total_flos": 8.792910420571587e+17,
|
| 6025 |
"train_batch_size": 2,
|
| 6026 |
"trial_name": null,
|
| 6027 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eb97127f3633f0387d329b923ad0716a30b1001fb17ad9a7247f8ed8a4f5dab
|
| 3 |
size 5777
|