Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0a59517e4a01479864ee5d89d301a8a00f989766f263f6776c0bd7ac658eef
+oid sha256:05168bcf41d42782e54f2110629a07f6dfe491410f4a0c12e5c2ab3d90836271
 size 161515608

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777aa2f3c1c30caa4a52015147ada8dfe521150c7bcc0e8604bc28f2deed2ef2
+oid sha256:dd295a28962bd0b73c87cd25e49b90c33ee4984b4d89fb83894543530a2dc2f7
 size 323181259

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b0cc75c21e30eb630a9fff29b7a6e24e8501ef27a94592e859fd7084f223ef
+oid sha256:6ef3bc6f4d35776f47009c7dd438a2c3372feb65dbb821c4678645626f6d1776
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.398467432950191,
+  "epoch": 4.245210727969349,
   "eval_steps": 500,
-  "global_step": 145,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,56 +1408,6 @@
       "mean_token_accuracy": 0.9439713805913925,
       "num_tokens": 251133.0,
       "step": 140
-    },
-    {
-      "entropy": 0.7664961665868759,
-      "epoch": 4.275862068965517,
-      "grad_norm": 4.1875,
-      "learning_rate": 2.0096189432334194e-06,
-      "loss": 0.251,
-      "mean_token_accuracy": 0.9318085461854935,
-      "num_tokens": 253030.0,
-      "step": 141
-    },
-    {
-      "entropy": 0.7621353343129158,
-      "epoch": 4.306513409961686,
-      "grad_norm": 4.59375,
-      "learning_rate": 1.8553997993420495e-06,
-      "loss": 0.2019,
-      "mean_token_accuracy": 0.9506975933909416,
-      "num_tokens": 254683.0,
-      "step": 142
-    },
-    {
-      "entropy": 0.7942825853824615,
-      "epoch": 4.337164750957855,
-      "grad_norm": 7.5625,
-      "learning_rate": 1.706946311531779e-06,
-      "loss": 0.3202,
-      "mean_token_accuracy": 0.9199245423078537,
-      "num_tokens": 256339.0,
-      "step": 143
-    },
-    {
-      "entropy": 0.7943987771868706,
-      "epoch": 4.3678160919540225,
-      "grad_norm": 5.15625,
-      "learning_rate": 1.5643235964088065e-06,
-      "loss": 0.2463,
-      "mean_token_accuracy": 0.9323071017861366,
-      "num_tokens": 257877.0,
-      "step": 144
-    },
-    {
-      "entropy": 0.7164058461785316,
-      "epoch": 4.398467432950191,
-      "grad_norm": 13.4375,
-      "learning_rate": 1.4275942130097097e-06,
-      "loss": 0.1929,
-      "mean_token_accuracy": 0.9492844417691231,
-      "num_tokens": 259301.0,
-      "step": 145
     }
   ],
   "logging_steps": 1,
@@ -1477,7 +1427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6865836098592768.0,
+  "total_flos": 6665368235175936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null