Upload checkpoint-3330
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +75 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4e0a7bce7d7d89e8783efccc7a1906bf73afdf549c6ef81eb00b9261e058f76
|
| 3 |
+
size 861966906
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c740ceedd35a621232bb4f9850afdd7ac0cbb3d6113eebc2f00ed437f59bcbcc
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:243e8de64f4f19d16558eb6f5b4a77ed28295d1f7205fc19fb8d2b20be1c6b46
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3330,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.5015015015015014,
|
| 13 |
+
"grad_norm": 6.153151035308838,
|
| 14 |
+
"learning_rate": 1.6996996996997e-05,
|
| 15 |
+
"loss": 0.4513,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 3.003003003003003,
|
| 20 |
+
"grad_norm": 3.031472682952881,
|
| 21 |
+
"learning_rate": 1.3993993993993995e-05,
|
| 22 |
+
"loss": 0.2028,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 4.504504504504505,
|
| 27 |
+
"grad_norm": 5.592371463775635,
|
| 28 |
+
"learning_rate": 1.0990990990990992e-05,
|
| 29 |
+
"loss": 0.0989,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 6.006006006006006,
|
| 34 |
+
"grad_norm": 6.730876922607422,
|
| 35 |
+
"learning_rate": 7.987987987987988e-06,
|
| 36 |
+
"loss": 0.0639,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 7.5075075075075075,
|
| 41 |
+
"grad_norm": 3.5161945819854736,
|
| 42 |
+
"learning_rate": 4.984984984984985e-06,
|
| 43 |
+
"loss": 0.0354,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 9.00900900900901,
|
| 48 |
+
"grad_norm": 1.2440450191497803,
|
| 49 |
+
"learning_rate": 1.9819819819819822e-06,
|
| 50 |
+
"loss": 0.0226,
|
| 51 |
+
"step": 3000
|
| 52 |
+
}
|
| 53 |
+
],
|
| 54 |
+
"logging_steps": 500,
|
| 55 |
+
"max_steps": 3330,
|
| 56 |
+
"num_input_tokens_seen": 0,
|
| 57 |
+
"num_train_epochs": 10,
|
| 58 |
+
"save_steps": 500,
|
| 59 |
+
"stateful_callbacks": {
|
| 60 |
+
"TrainerControl": {
|
| 61 |
+
"args": {
|
| 62 |
+
"should_epoch_stop": false,
|
| 63 |
+
"should_evaluate": false,
|
| 64 |
+
"should_log": false,
|
| 65 |
+
"should_save": true,
|
| 66 |
+
"should_training_stop": true
|
| 67 |
+
},
|
| 68 |
+
"attributes": {}
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"total_flos": 881535684193692.0,
|
| 72 |
+
"train_batch_size": 32,
|
| 73 |
+
"trial_name": null,
|
| 74 |
+
"trial_params": null
|
| 75 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0923cb67eec298fb57a54228d2c594c9d9362cf341cac55b8b4beb0751769a25
|
| 3 |
+
size 5048
|