Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11e80c2626b7e725c36b5d59e4313d238413de8eebfdb5b1d6b6e28ab8c714b
+oid sha256:aea01fe0dd2af8bf4b4d060ddad5d472a16722fc394fcb4b38e130025fbdd9a6
 size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d135c01136a11bcef2ed383e09bc32d52fff97352f14798fe440aa0238e742
+oid sha256:a6dfd7167bc860806832aeae1caf4b2e1b91ea75533b6f21aba040240609424c
 size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3698f87a076ace386d58713681a24c766465261225a60a74e4631003e3b501c
+oid sha256:8be5a9156a087de7426b7455c1cfa58b09ad84e7aaa003d8794e888b3cdd82ad
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4372b8bc129cb832d61f89de539110be4b375eeb5fe693144c4dd880623a9aaf
+oid sha256:3bf1e902c3114bb5312c2c178dc4d942be3a06cb5931cabbb4ddb7748d0f53ee
 size 1064

trainer_state.json

@@ -1,164 +1,218 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9846153846153847,
+  "epoch": 0.9990680335507922,
   "eval_steps": 500,
-  "global_step": 48,
+  "global_step": 67,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.6235,
+      "loss": 2.0684,
       "step": 2
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.06,
       "learning_rate": 2e-05,
-      "loss": 1.878,
+      "loss": 1.2351,
       "step": 4
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.09,
       "learning_rate": 2e-05,
-      "loss": 1.8871,
+      "loss": 1.0218,
       "step": 6
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.9954,
+      "loss": 0.944,
       "step": 8
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.15,
       "learning_rate": 2e-05,
-      "loss": 2.0806,
+      "loss": 1.0419,
       "step": 10
     },
     {
-      "epoch": 0.25,
+      "epoch": 0.18,
       "learning_rate": 2e-05,
-      "loss": 2.0435,
+      "loss": 1.0514,
       "step": 12
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 1.6826,
+      "loss": 1.4716,
       "step": 14
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.24,
       "learning_rate": 2e-05,
-      "loss": 1.5779,
+      "loss": 1.9171,
       "step": 16
     },
     {
-      "epoch": 0.37,
+      "epoch": 0.27,
       "learning_rate": 2e-05,
-      "loss": 1.9058,
+      "loss": 1.8928,
       "step": 18
     },
     {
-      "epoch": 0.41,
+      "epoch": 0.3,
       "learning_rate": 2e-05,
-      "loss": 1.6972,
+      "loss": 1.0043,
       "step": 20
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.9398,
+      "loss": 0.9942,
       "step": 22
     },
     {
-      "epoch": 0.49,
+      "epoch": 0.36,
       "learning_rate": 2e-05,
-      "loss": 1.9236,
+      "loss": 1.0396,
       "step": 24
     },
     {
-      "epoch": 0.53,
+      "epoch": 0.39,
       "learning_rate": 2e-05,
-      "loss": 1.6062,
+      "loss": 0.7804,
       "step": 26
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.42,
       "learning_rate": 2e-05,
-      "loss": 1.7559,
+      "loss": 1.0986,
       "step": 28
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.9474,
+      "loss": 1.3254,
       "step": 30
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.48,
       "learning_rate": 2e-05,
-      "loss": 1.7649,
+      "loss": 1.4412,
       "step": 32
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.51,
       "learning_rate": 2e-05,
-      "loss": 1.7762,
+      "loss": 1.533,
       "step": 34
     },
     {
-      "epoch": 0.74,
+      "epoch": 0.54,
       "learning_rate": 2e-05,
-      "loss": 2.011,
+      "loss": 1.2709,
       "step": 36
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.6693,
+      "loss": 0.8853,
       "step": 38
     },
     {
-      "epoch": 0.82,
+      "epoch": 0.6,
       "learning_rate": 2e-05,
-      "loss": 1.8561,
+      "loss": 1.0464,
       "step": 40
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.63,
       "learning_rate": 2e-05,
-      "loss": 1.9452,
+      "loss": 0.8004,
       "step": 42
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.9725,
+      "loss": 0.8526,
       "step": 44
     },
     {
-      "epoch": 0.94,
+      "epoch": 0.69,
       "learning_rate": 2e-05,
-      "loss": 1.8454,
+      "loss": 1.1846,
       "step": 46
     },
     {
-      "epoch": 0.98,
+      "epoch": 0.72,
       "learning_rate": 2e-05,
-      "loss": 1.8836,
+      "loss": 1.3307,
       "step": 48
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2e-05,
+      "loss": 1.9532,
+      "step": 50
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2e-05,
+      "loss": 0.9404,
+      "step": 52
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2e-05,
+      "loss": 0.9675,
+      "step": 54
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2e-05,
+      "loss": 0.8579,
+      "step": 56
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2e-05,
+      "loss": 0.9398,
+      "step": 58
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2e-05,
+      "loss": 1.045,
+      "step": 60
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2e-05,
+      "loss": 1.1489,
+      "step": 62
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2e-05,
+      "loss": 1.1677,
+      "step": 64
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2e-05,
+      "loss": 1.1349,
+      "step": 66
     }
   ],
   "logging_steps": 2,
-  "max_steps": 144,
+  "max_steps": 67,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.901574003725107e+16,
+  "total_flos": 2.539821361058611e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1142229c66bf3f832461258a15f379deffb2b5691470e753d093d27a4adb154c
+oid sha256:97d5f0e37cf4b722c6518f8cfa86a35259d2a47813b4394ade22d5e08cffdbf4
 size 4728