Upload 12 files
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +663 -33
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"k_proj",
|
| 23 |
"gate_proj",
|
| 24 |
-
"up_proj",
|
| 25 |
"q_proj",
|
| 26 |
"v_proj",
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
| 31 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"o_proj",
|
| 23 |
"k_proj",
|
| 24 |
"gate_proj",
|
|
|
|
| 25 |
"q_proj",
|
| 26 |
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
| 31 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100059752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21f1402c48f90b44fe71d7d2f4a3984a548e64279efda68f4b24e55ada2c8233
|
| 3 |
size 100059752
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50545780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:502a6742bb8f48b47e6450a524e1d895f6e64d98a1cb546233bd8cc6428c1988
|
| 3 |
size 50545780
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e32a00d1dc583ddebb6ee0c3b9cb549aa96ce10f763167188e46f4b89e143b
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,90 +1,720 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 0.0001,
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 2.0,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 3.0,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss":
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 4.0,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 5.0,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 6.0,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 7.0,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 8.0,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 9.0,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 10.0,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
}
|
| 81 |
],
|
| 82 |
"logging_steps": 1,
|
| 83 |
-
"max_steps":
|
| 84 |
"num_input_tokens_seen": 0,
|
| 85 |
-
"num_train_epochs":
|
| 86 |
"save_steps": 500,
|
| 87 |
-
"total_flos":
|
| 88 |
"train_batch_size": 1,
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.355809211730957,
|
| 14 |
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 1.3272,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 2.355809211730957,
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 1.3272,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 1.4446067810058594,
|
| 28 |
+
"learning_rate": 0.00019795918367346938,
|
| 29 |
+
"loss": 1.1654,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 1.521039366722107,
|
| 35 |
+
"learning_rate": 0.0001959183673469388,
|
| 36 |
+
"loss": 0.9031,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 1.5087562799453735,
|
| 42 |
+
"learning_rate": 0.00019387755102040816,
|
| 43 |
+
"loss": 0.6727,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 1.60162353515625,
|
| 49 |
+
"learning_rate": 0.00019183673469387756,
|
| 50 |
+
"loss": 0.4641,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 1.0103554725646973,
|
| 56 |
+
"learning_rate": 0.00018979591836734697,
|
| 57 |
+
"loss": 0.2926,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 2.812863826751709,
|
| 63 |
+
"learning_rate": 0.00018775510204081634,
|
| 64 |
+
"loss": 0.2053,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 1.5256155729293823,
|
| 70 |
+
"learning_rate": 0.00018571428571428572,
|
| 71 |
+
"loss": 0.1473,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 1.875736951828003,
|
| 77 |
+
"learning_rate": 0.00018367346938775512,
|
| 78 |
+
"loss": 0.1351,
|
| 79 |
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.0,
|
| 83 |
+
"grad_norm": 0.4695473313331604,
|
| 84 |
+
"learning_rate": 0.0001816326530612245,
|
| 85 |
+
"loss": 0.1029,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.0,
|
| 90 |
+
"grad_norm": 0.5592666864395142,
|
| 91 |
+
"learning_rate": 0.0001795918367346939,
|
| 92 |
+
"loss": 0.0982,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.0,
|
| 97 |
+
"grad_norm": 0.3424108922481537,
|
| 98 |
+
"learning_rate": 0.00017755102040816327,
|
| 99 |
+
"loss": 0.086,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.0,
|
| 104 |
+
"grad_norm": 0.5507439374923706,
|
| 105 |
+
"learning_rate": 0.00017551020408163265,
|
| 106 |
+
"loss": 0.082,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.0,
|
| 111 |
+
"grad_norm": 0.40908390283584595,
|
| 112 |
+
"learning_rate": 0.00017346938775510205,
|
| 113 |
+
"loss": 0.0727,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.0,
|
| 118 |
+
"grad_norm": 0.5264757871627808,
|
| 119 |
+
"learning_rate": 0.00017142857142857143,
|
| 120 |
+
"loss": 0.0651,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.0,
|
| 125 |
+
"grad_norm": 0.5899124145507812,
|
| 126 |
+
"learning_rate": 0.00016938775510204083,
|
| 127 |
+
"loss": 0.0557,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.0,
|
| 132 |
+
"grad_norm": 0.5028952956199646,
|
| 133 |
+
"learning_rate": 0.00016734693877551023,
|
| 134 |
+
"loss": 0.042,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.0,
|
| 139 |
+
"grad_norm": 0.6451049447059631,
|
| 140 |
+
"learning_rate": 0.0001653061224489796,
|
| 141 |
+
"loss": 0.0315,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 20.0,
|
| 146 |
+
"grad_norm": 0.5155397057533264,
|
| 147 |
+
"learning_rate": 0.00016326530612244898,
|
| 148 |
+
"loss": 0.017,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.0,
|
| 153 |
+
"grad_norm": 0.29147273302078247,
|
| 154 |
+
"learning_rate": 0.00016122448979591838,
|
| 155 |
+
"loss": 0.009,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 22.0,
|
| 160 |
+
"grad_norm": 0.3708033263683319,
|
| 161 |
+
"learning_rate": 0.00015918367346938776,
|
| 162 |
+
"loss": 0.0076,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 23.0,
|
| 167 |
+
"grad_norm": 0.08893364667892456,
|
| 168 |
+
"learning_rate": 0.00015714285714285716,
|
| 169 |
+
"loss": 0.0057,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 24.0,
|
| 174 |
+
"grad_norm": 0.1690322905778885,
|
| 175 |
+
"learning_rate": 0.00015510204081632654,
|
| 176 |
+
"loss": 0.0062,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 25.0,
|
| 181 |
+
"grad_norm": 0.20433245599269867,
|
| 182 |
+
"learning_rate": 0.0001530612244897959,
|
| 183 |
+
"loss": 0.0058,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 26.0,
|
| 188 |
+
"grad_norm": 0.16720539331436157,
|
| 189 |
+
"learning_rate": 0.0001510204081632653,
|
| 190 |
+
"loss": 0.0056,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 27.0,
|
| 195 |
+
"grad_norm": 0.17153231799602509,
|
| 196 |
+
"learning_rate": 0.00014897959183673472,
|
| 197 |
+
"loss": 0.0056,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 28.0,
|
| 202 |
+
"grad_norm": 0.1037655845284462,
|
| 203 |
+
"learning_rate": 0.0001469387755102041,
|
| 204 |
+
"loss": 0.0059,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 29.0,
|
| 209 |
+
"grad_norm": 0.14174027740955353,
|
| 210 |
+
"learning_rate": 0.0001448979591836735,
|
| 211 |
+
"loss": 0.0055,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 30.0,
|
| 216 |
+
"grad_norm": 0.011748074553906918,
|
| 217 |
+
"learning_rate": 0.00014285714285714287,
|
| 218 |
+
"loss": 0.0053,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 31.0,
|
| 223 |
+
"grad_norm": 0.09256725758314133,
|
| 224 |
+
"learning_rate": 0.00014081632653061224,
|
| 225 |
+
"loss": 0.0054,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 32.0,
|
| 230 |
+
"grad_norm": 0.09271395206451416,
|
| 231 |
+
"learning_rate": 0.00013877551020408165,
|
| 232 |
+
"loss": 0.0054,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 33.0,
|
| 237 |
+
"grad_norm": 0.10514255613088608,
|
| 238 |
+
"learning_rate": 0.00013673469387755102,
|
| 239 |
+
"loss": 0.0049,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 34.0,
|
| 244 |
+
"grad_norm": 0.14201119542121887,
|
| 245 |
+
"learning_rate": 0.0001346938775510204,
|
| 246 |
+
"loss": 0.0055,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 35.0,
|
| 251 |
+
"grad_norm": 0.05419391393661499,
|
| 252 |
+
"learning_rate": 0.0001326530612244898,
|
| 253 |
+
"loss": 0.0049,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 36.0,
|
| 258 |
+
"grad_norm": 0.17390480637550354,
|
| 259 |
+
"learning_rate": 0.00013061224489795917,
|
| 260 |
+
"loss": 0.0056,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 37.0,
|
| 265 |
+
"grad_norm": 0.01634000428020954,
|
| 266 |
+
"learning_rate": 0.00012857142857142858,
|
| 267 |
+
"loss": 0.0053,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 38.0,
|
| 272 |
+
"grad_norm": 0.14033198356628418,
|
| 273 |
+
"learning_rate": 0.00012653061224489798,
|
| 274 |
+
"loss": 0.0055,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 39.0,
|
| 279 |
+
"grad_norm": 0.06495083123445511,
|
| 280 |
+
"learning_rate": 0.00012448979591836735,
|
| 281 |
+
"loss": 0.0053,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 40.0,
|
| 286 |
+
"grad_norm": 0.014886317774653435,
|
| 287 |
+
"learning_rate": 0.00012244897959183676,
|
| 288 |
+
"loss": 0.0053,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 41.0,
|
| 293 |
+
"grad_norm": 0.09001646935939789,
|
| 294 |
+
"learning_rate": 0.00012040816326530613,
|
| 295 |
+
"loss": 0.0054,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 42.0,
|
| 300 |
+
"grad_norm": 0.05034321919083595,
|
| 301 |
+
"learning_rate": 0.00011836734693877552,
|
| 302 |
+
"loss": 0.0048,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 43.0,
|
| 307 |
+
"grad_norm": 0.012698125094175339,
|
| 308 |
+
"learning_rate": 0.0001163265306122449,
|
| 309 |
+
"loss": 0.0053,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 44.0,
|
| 314 |
+
"grad_norm": 0.06450632214546204,
|
| 315 |
+
"learning_rate": 0.00011428571428571428,
|
| 316 |
+
"loss": 0.0053,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 45.0,
|
| 321 |
+
"grad_norm": 0.06438387930393219,
|
| 322 |
+
"learning_rate": 0.00011224489795918367,
|
| 323 |
+
"loss": 0.0053,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 46.0,
|
| 328 |
+
"grad_norm": 0.010477419942617416,
|
| 329 |
+
"learning_rate": 0.00011020408163265306,
|
| 330 |
+
"loss": 0.0053,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 47.0,
|
| 335 |
+
"grad_norm": 0.010764668695628643,
|
| 336 |
+
"learning_rate": 0.00010816326530612246,
|
| 337 |
+
"loss": 0.0053,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 48.0,
|
| 342 |
+
"grad_norm": 0.010250415652990341,
|
| 343 |
+
"learning_rate": 0.00010612244897959185,
|
| 344 |
+
"loss": 0.0053,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 49.0,
|
| 349 |
+
"grad_norm": 0.01072185579687357,
|
| 350 |
+
"learning_rate": 0.00010408163265306123,
|
| 351 |
+
"loss": 0.0053,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 50.0,
|
| 356 |
+
"grad_norm": 0.04789392277598381,
|
| 357 |
+
"learning_rate": 0.00010204081632653062,
|
| 358 |
+
"loss": 0.0058,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 51.0,
|
| 363 |
+
"grad_norm": 0.046109408140182495,
|
| 364 |
+
"learning_rate": 0.0001,
|
| 365 |
+
"loss": 0.0048,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 52.0,
|
| 370 |
+
"grad_norm": 0.06478489935398102,
|
| 371 |
+
"learning_rate": 9.79591836734694e-05,
|
| 372 |
+
"loss": 0.0053,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 53.0,
|
| 377 |
+
"grad_norm": 0.06432071328163147,
|
| 378 |
+
"learning_rate": 9.591836734693878e-05,
|
| 379 |
+
"loss": 0.0053,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 54.0,
|
| 384 |
+
"grad_norm": 0.02735786698758602,
|
| 385 |
+
"learning_rate": 9.387755102040817e-05,
|
| 386 |
+
"loss": 0.0058,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 55.0,
|
| 391 |
+
"grad_norm": 0.04583168402314186,
|
| 392 |
+
"learning_rate": 9.183673469387756e-05,
|
| 393 |
+
"loss": 0.0048,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 56.0,
|
| 398 |
+
"grad_norm": 0.08271433413028717,
|
| 399 |
+
"learning_rate": 8.979591836734695e-05,
|
| 400 |
+
"loss": 0.0053,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 57.0,
|
| 405 |
+
"grad_norm": 0.010216895490884781,
|
| 406 |
+
"learning_rate": 8.775510204081632e-05,
|
| 407 |
+
"loss": 0.0053,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 58.0,
|
| 412 |
+
"grad_norm": 0.06349101662635803,
|
| 413 |
+
"learning_rate": 8.571428571428571e-05,
|
| 414 |
+
"loss": 0.0053,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 59.0,
|
| 419 |
+
"grad_norm": 0.06379684805870056,
|
| 420 |
+
"learning_rate": 8.367346938775511e-05,
|
| 421 |
+
"loss": 0.0053,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 60.0,
|
| 426 |
+
"grad_norm": 0.010050535202026367,
|
| 427 |
+
"learning_rate": 8.163265306122449e-05,
|
| 428 |
+
"loss": 0.0053,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 61.0,
|
| 433 |
+
"grad_norm": 0.08275067806243896,
|
| 434 |
+
"learning_rate": 7.959183673469388e-05,
|
| 435 |
+
"loss": 0.0053,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 62.0,
|
| 440 |
+
"grad_norm": 0.010069911368191242,
|
| 441 |
+
"learning_rate": 7.755102040816327e-05,
|
| 442 |
+
"loss": 0.0053,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 63.0,
|
| 447 |
+
"grad_norm": 0.00969759002327919,
|
| 448 |
+
"learning_rate": 7.551020408163266e-05,
|
| 449 |
+
"loss": 0.0053,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 64.0,
|
| 454 |
+
"grad_norm": 0.06372305005788803,
|
| 455 |
+
"learning_rate": 7.346938775510205e-05,
|
| 456 |
+
"loss": 0.0053,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 65.0,
|
| 461 |
+
"grad_norm": 0.027780011296272278,
|
| 462 |
+
"learning_rate": 7.142857142857143e-05,
|
| 463 |
+
"loss": 0.0048,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 66.0,
|
| 468 |
+
"grad_norm": 0.009718519635498524,
|
| 469 |
+
"learning_rate": 6.938775510204082e-05,
|
| 470 |
+
"loss": 0.0053,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 67.0,
|
| 475 |
+
"grad_norm": 0.04677029326558113,
|
| 476 |
+
"learning_rate": 6.73469387755102e-05,
|
| 477 |
+
"loss": 0.0058,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 68.0,
|
| 482 |
+
"grad_norm": 0.00952499732375145,
|
| 483 |
+
"learning_rate": 6.530612244897959e-05,
|
| 484 |
+
"loss": 0.0053,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 69.0,
|
| 489 |
+
"grad_norm": 0.009604902006685734,
|
| 490 |
+
"learning_rate": 6.326530612244899e-05,
|
| 491 |
+
"loss": 0.0053,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 70.0,
|
| 496 |
+
"grad_norm": 0.06420488655567169,
|
| 497 |
+
"learning_rate": 6.122448979591838e-05,
|
| 498 |
+
"loss": 0.0053,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 71.0,
|
| 503 |
+
"grad_norm": 0.026840027421712875,
|
| 504 |
+
"learning_rate": 5.918367346938776e-05,
|
| 505 |
+
"loss": 0.0058,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 72.0,
|
| 510 |
+
"grad_norm": 0.009567616507411003,
|
| 511 |
+
"learning_rate": 5.714285714285714e-05,
|
| 512 |
+
"loss": 0.0053,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 73.0,
|
| 517 |
+
"grad_norm": 0.045753173530101776,
|
| 518 |
+
"learning_rate": 5.510204081632653e-05,
|
| 519 |
+
"loss": 0.0048,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 74.0,
|
| 524 |
+
"grad_norm": 0.009476774372160435,
|
| 525 |
+
"learning_rate": 5.3061224489795926e-05,
|
| 526 |
+
"loss": 0.0053,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 75.0,
|
| 531 |
+
"grad_norm": 0.04571187496185303,
|
| 532 |
+
"learning_rate": 5.102040816326531e-05,
|
| 533 |
+
"loss": 0.0048,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 76.0,
|
| 538 |
+
"grad_norm": 0.009730060584843159,
|
| 539 |
+
"learning_rate": 4.89795918367347e-05,
|
| 540 |
+
"loss": 0.0053,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 77.0,
|
| 545 |
+
"grad_norm": 0.028138577938079834,
|
| 546 |
+
"learning_rate": 4.6938775510204086e-05,
|
| 547 |
+
"loss": 0.0048,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 78.0,
|
| 552 |
+
"grad_norm": 0.06447193771600723,
|
| 553 |
+
"learning_rate": 4.4897959183673474e-05,
|
| 554 |
+
"loss": 0.0053,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 79.0,
|
| 559 |
+
"grad_norm": 0.06447941064834595,
|
| 560 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 561 |
+
"loss": 0.0053,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 80.0,
|
| 566 |
+
"grad_norm": 0.028326738625764847,
|
| 567 |
+
"learning_rate": 4.0816326530612245e-05,
|
| 568 |
+
"loss": 0.0048,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 81.0,
|
| 573 |
+
"grad_norm": 0.08396949619054794,
|
| 574 |
+
"learning_rate": 3.8775510204081634e-05,
|
| 575 |
+
"loss": 0.0053,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 82.0,
|
| 580 |
+
"grad_norm": 0.04610452800989151,
|
| 581 |
+
"learning_rate": 3.673469387755102e-05,
|
| 582 |
+
"loss": 0.0048,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 83.0,
|
| 587 |
+
"grad_norm": 0.046097833663225174,
|
| 588 |
+
"learning_rate": 3.469387755102041e-05,
|
| 589 |
+
"loss": 0.0048,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 84.0,
|
| 594 |
+
"grad_norm": 0.009920083917677402,
|
| 595 |
+
"learning_rate": 3.265306122448979e-05,
|
| 596 |
+
"loss": 0.0053,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 85.0,
|
| 601 |
+
"grad_norm": 0.02849722094833851,
|
| 602 |
+
"learning_rate": 3.061224489795919e-05,
|
| 603 |
+
"loss": 0.0048,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 86.0,
|
| 608 |
+
"grad_norm": 0.00956336036324501,
|
| 609 |
+
"learning_rate": 2.857142857142857e-05,
|
| 610 |
+
"loss": 0.0053,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 87.0,
|
| 615 |
+
"grad_norm": 0.06530480086803436,
|
| 616 |
+
"learning_rate": 2.6530612244897963e-05,
|
| 617 |
+
"loss": 0.0053,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 88.0,
|
| 622 |
+
"grad_norm": 0.028555840253829956,
|
| 623 |
+
"learning_rate": 2.448979591836735e-05,
|
| 624 |
+
"loss": 0.0048,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 89.0,
|
| 629 |
+
"grad_norm": 0.009486482478678226,
|
| 630 |
+
"learning_rate": 2.2448979591836737e-05,
|
| 631 |
+
"loss": 0.0053,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 90.0,
|
| 636 |
+
"grad_norm": 0.028627220541238785,
|
| 637 |
+
"learning_rate": 2.0408163265306123e-05,
|
| 638 |
+
"loss": 0.0048,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 91.0,
|
| 643 |
+
"grad_norm": 0.009754066355526447,
|
| 644 |
+
"learning_rate": 1.836734693877551e-05,
|
| 645 |
+
"loss": 0.0053,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 92.0,
|
| 650 |
+
"grad_norm": 0.009760790504515171,
|
| 651 |
+
"learning_rate": 1.6326530612244897e-05,
|
| 652 |
+
"loss": 0.0053,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 93.0,
|
| 657 |
+
"grad_norm": 0.02760305069386959,
|
| 658 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 659 |
+
"loss": 0.0058,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 94.0,
|
| 664 |
+
"grad_norm": 0.009988558478653431,
|
| 665 |
+
"learning_rate": 1.2244897959183674e-05,
|
| 666 |
+
"loss": 0.0053,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 95.0,
|
| 671 |
+
"grad_norm": 0.04651060700416565,
|
| 672 |
+
"learning_rate": 1.0204081632653061e-05,
|
| 673 |
+
"loss": 0.0048,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 96.0,
|
| 678 |
+
"grad_norm": 0.010227691382169724,
|
| 679 |
+
"learning_rate": 8.163265306122448e-06,
|
| 680 |
+
"loss": 0.0053,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 97.0,
|
| 685 |
+
"grad_norm": 0.010372389107942581,
|
| 686 |
+
"learning_rate": 6.122448979591837e-06,
|
| 687 |
+
"loss": 0.0053,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 98.0,
|
| 692 |
+
"grad_norm": 0.009753258898854256,
|
| 693 |
+
"learning_rate": 4.081632653061224e-06,
|
| 694 |
+
"loss": 0.0053,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 99.0,
|
| 699 |
+
"grad_norm": 0.010054420679807663,
|
| 700 |
+
"learning_rate": 2.040816326530612e-06,
|
| 701 |
+
"loss": 0.0053,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 100.0,
|
| 706 |
+
"grad_norm": 0.01012208592146635,
|
| 707 |
+
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.0053,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
| 713 |
+
"max_steps": 100,
|
| 714 |
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 100,
|
| 716 |
"save_steps": 500,
|
| 717 |
+
"total_flos": 625210570752000.0,
|
| 718 |
"train_batch_size": 1,
|
| 719 |
"trial_name": null,
|
| 720 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc2b910d926edadac64591186b55a95c20e3f121f861011f15403c335b9a1351
|
| 3 |
size 4984
|