Training in progress, step 100
Browse files- all_results.json +9 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
- train_results.json +9 -0
- trainer_state.json +56 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.08664339780807495,
|
| 5 |
+
"train_runtime": 32.2678,
|
| 6 |
+
"train_samples": 50,
|
| 7 |
+
"train_samples_per_second": 1.55,
|
| 8 |
+
"train_steps_per_second": 0.031
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.44.1"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2200119864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:854d0599516862bbac2f52436f10412332754ea3872e4e1d9d4a4b8e0f8452a4
|
| 3 |
size 2200119864
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 0.0,
|
| 4 |
+
"train_loss": 0.08664339780807495,
|
| 5 |
+
"train_runtime": 32.2678,
|
| 6 |
+
"train_samples": 50,
|
| 7 |
+
"train_samples_per_second": 1.55,
|
| 8 |
+
"train_steps_per_second": 0.031
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 1,
|
| 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 |
+
"learning_rate": 5e-07,
|
| 14 |
+
"logits/chosen": -2.2653555870056152,
|
| 15 |
+
"logits/rejected": -2.23056960105896,
|
| 16 |
+
"logps/chosen": -136.37684631347656,
|
| 17 |
+
"logps/rejected": -110.164306640625,
|
| 18 |
+
"loss": 0.0866,
|
| 19 |
+
"rewards/accuracies": 0.0,
|
| 20 |
+
"rewards/chosen": 0.0,
|
| 21 |
+
"rewards/margins": 0.0,
|
| 22 |
+
"rewards/rejected": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"step": 1,
|
| 28 |
+
"total_flos": 0.0,
|
| 29 |
+
"train_loss": 0.08664339780807495,
|
| 30 |
+
"train_runtime": 32.2678,
|
| 31 |
+
"train_samples_per_second": 1.55,
|
| 32 |
+
"train_steps_per_second": 0.031
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"logging_steps": 10,
|
| 36 |
+
"max_steps": 1,
|
| 37 |
+
"num_input_tokens_seen": 0,
|
| 38 |
+
"num_train_epochs": 1,
|
| 39 |
+
"save_steps": 100,
|
| 40 |
+
"stateful_callbacks": {
|
| 41 |
+
"TrainerControl": {
|
| 42 |
+
"args": {
|
| 43 |
+
"should_epoch_stop": false,
|
| 44 |
+
"should_evaluate": false,
|
| 45 |
+
"should_log": false,
|
| 46 |
+
"should_save": true,
|
| 47 |
+
"should_training_stop": true
|
| 48 |
+
},
|
| 49 |
+
"attributes": {}
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"total_flos": 0.0,
|
| 53 |
+
"train_batch_size": 16,
|
| 54 |
+
"trial_name": null,
|
| 55 |
+
"trial_params": null
|
| 56 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7608
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41eacf8e17026ccc6952859b3bfad36fd11344e07a744a05ba55153cd0e5bdaf
|
| 3 |
size 7608
|