Training in progress, step 1200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14708920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc237175d1c9e53b372d17b396ea8aaa0ff529c2ff509ea1b2f3ebfa668de45a
|
| 3 |
size 14708920
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bbadb3672fa92ac893836ffef993ebcdbf5839a47ab535a9654484e016aafe8
|
| 3 |
+
size 8183389
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b396e67165358d56b909df6bed988ef6af62fd5862cc21b4c43bd0b90bf5bef1
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c707213911f6b638fe6faf3e580c511e73baf957e82393d3ad4d00744c57f46
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -72,13 +72,26 @@
|
|
| 72 |
"eval_samples_per_second": 2.219,
|
| 73 |
"eval_steps_per_second": 0.278,
|
| 74 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
}
|
| 76 |
],
|
| 77 |
"logging_steps": 200,
|
| 78 |
"max_steps": 1593,
|
| 79 |
"num_train_epochs": 3,
|
| 80 |
"save_steps": 200,
|
| 81 |
-
"total_flos": 2.
|
| 82 |
"trial_name": null,
|
| 83 |
"trial_params": null
|
| 84 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.2590966122961103,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 72 |
"eval_samples_per_second": 2.219,
|
| 73 |
"eval_steps_per_second": 0.278,
|
| 74 |
"step": 1000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.26,
|
| 78 |
+
"learning_rate": 2e-05,
|
| 79 |
+
"loss": 0.6355,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.26,
|
| 84 |
+
"eval_runtime": 1008.6366,
|
| 85 |
+
"eval_samples_per_second": 2.231,
|
| 86 |
+
"eval_steps_per_second": 0.28,
|
| 87 |
+
"step": 1200
|
| 88 |
}
|
| 89 |
],
|
| 90 |
"logging_steps": 200,
|
| 91 |
"max_steps": 1593,
|
| 92 |
"num_train_epochs": 3,
|
| 93 |
"save_steps": 200,
|
| 94 |
+
"total_flos": 2.6799726998677094e+17,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
| 97 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ce7a666499246718271a34efa2b96b7c1aa21dc0a0fa410dedb2d1a1c4790d
|
| 3 |
size 4027
|