Training in progress, step 2840, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81bb0ca4c8d3f0b7df4168a6f129ab6659286d7cc50f721d7d619b912b04441c
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da701cf784e178c8d5cc5b6be4781f56ce0027e182866707b0b6d82d08f50d0
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac8ce587a1f63693d985c5a1ab868e6efb026b5e08677b84eaca40b9a02b9058
|
| 3 |
size 14645
|
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:ba1b53ed33622e17fae8a729aa45522b55318b24cb423fed2491721f07b63a63
|
| 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": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2848,6 +2848,16 @@
|
|
| 2848 |
"mean_token_accuracy": 0.7598815195262432,
|
| 2849 |
"num_tokens": 13163748.0,
|
| 2850 |
"step": 2830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2851 |
}
|
| 2852 |
],
|
| 2853 |
"logging_steps": 10,
|
|
@@ -2867,7 +2877,7 @@
|
|
| 2867 |
"attributes": {}
|
| 2868 |
}
|
| 2869 |
},
|
| 2870 |
-
"total_flos": 6.
|
| 2871 |
"train_batch_size": 4,
|
| 2872 |
"trial_name": null,
|
| 2873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6058666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2848 |
"mean_token_accuracy": 0.7598815195262432,
|
| 2849 |
"num_tokens": 13163748.0,
|
| 2850 |
"step": 2830
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"entropy": 0.8110849797725678,
|
| 2854 |
+
"epoch": 0.6058666666666667,
|
| 2855 |
+
"grad_norm": 0.3148553967475891,
|
| 2856 |
+
"learning_rate": 8.190159423236086e-05,
|
| 2857 |
+
"loss": 0.8950259208679199,
|
| 2858 |
+
"mean_token_accuracy": 0.7862283095717431,
|
| 2859 |
+
"num_tokens": 13204391.0,
|
| 2860 |
+
"step": 2840
|
| 2861 |
}
|
| 2862 |
],
|
| 2863 |
"logging_steps": 10,
|
|
|
|
| 2877 |
"attributes": {}
|
| 2878 |
}
|
| 2879 |
},
|
| 2880 |
+
"total_flos": 6.256929604727194e+16,
|
| 2881 |
"train_batch_size": 4,
|
| 2882 |
"trial_name": null,
|
| 2883 |
"trial_params": null
|