Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a797f551087e010ee19d4f64a47f7e6b7e8cd3368b6d09b6005ff7e655a959eb
+oid sha256:7b87905b967818bb58a7d8a98924637fd8e529c17e65d81fa4ba48b259e6a0a1
 size 293635024

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb48560a5b5da168faee233fb742ce90f8dea785af52ba490234711ffc29199
-size 587360954
+oid sha256:2bc6c06b142e47618bb27401d10a3629248fd822f97d5681c50f323b9668abef
+size 587361210

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8701b93e17a7f0e50887059a7c196dcbbaad17b98884e0b3fb9b08c6829c92a
+oid sha256:cd2dbb560b33d4689684d823717a94af32d66310a306a84655b09229b2cb70eb
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9721d5ba1fb05d41f214a5bebb8206b88b746e805209d13e654bce65e0ffa08
+oid sha256:d77a12c6ddcb588d8eb1fffa03b3e3be8b5f25c15acdb9a618c73413f62484db
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.963855421686747,
+  "epoch": 2.891566265060241,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,146 @@
       "learning_rate": 0.0001,
       "loss": 0.2676,
       "step": 100
+    },
+    {
+      "epoch": 1.0602409638554218,
+      "grad_norm": 0.1597064584493637,
+      "learning_rate": 0.0001,
+      "loss": 0.2644,
+      "step": 110
+    },
+    {
+      "epoch": 1.1566265060240963,
+      "grad_norm": 0.16861063241958618,
+      "learning_rate": 0.0001,
+      "loss": 0.2635,
+      "step": 120
+    },
+    {
+      "epoch": 1.2530120481927711,
+      "grad_norm": 0.1666216403245926,
+      "learning_rate": 0.0001,
+      "loss": 0.256,
+      "step": 130
+    },
+    {
+      "epoch": 1.3493975903614457,
+      "grad_norm": 0.1696414053440094,
+      "learning_rate": 0.0001,
+      "loss": 0.2529,
+      "step": 140
+    },
+    {
+      "epoch": 1.4457831325301205,
+      "grad_norm": 0.16793620586395264,
+      "learning_rate": 0.0001,
+      "loss": 0.2466,
+      "step": 150
+    },
+    {
+      "epoch": 1.5421686746987953,
+      "grad_norm": 0.19180789589881897,
+      "learning_rate": 0.0001,
+      "loss": 0.2446,
+      "step": 160
+    },
+    {
+      "epoch": 1.6385542168674698,
+      "grad_norm": 0.18770650029182434,
+      "learning_rate": 0.0001,
+      "loss": 0.2446,
+      "step": 170
+    },
+    {
+      "epoch": 1.7349397590361446,
+      "grad_norm": 0.1509401947259903,
+      "learning_rate": 0.0001,
+      "loss": 0.2418,
+      "step": 180
+    },
+    {
+      "epoch": 1.8313253012048194,
+      "grad_norm": 0.1551649123430252,
+      "learning_rate": 0.0001,
+      "loss": 0.2391,
+      "step": 190
+    },
+    {
+      "epoch": 1.927710843373494,
+      "grad_norm": 0.17986978590488434,
+      "learning_rate": 0.0001,
+      "loss": 0.2344,
+      "step": 200
+    },
+    {
+      "epoch": 2.0240963855421685,
+      "grad_norm": 0.20075887441635132,
+      "learning_rate": 0.0001,
+      "loss": 0.2304,
+      "step": 210
+    },
+    {
+      "epoch": 2.1204819277108435,
+      "grad_norm": 0.14372113347053528,
+      "learning_rate": 0.0001,
+      "loss": 0.2313,
+      "step": 220
+    },
+    {
+      "epoch": 2.216867469879518,
+      "grad_norm": 0.17301425337791443,
+      "learning_rate": 0.0001,
+      "loss": 0.2294,
+      "step": 230
+    },
+    {
+      "epoch": 2.3132530120481927,
+      "grad_norm": 0.1603270024061203,
+      "learning_rate": 0.0001,
+      "loss": 0.2238,
+      "step": 240
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "grad_norm": 0.1819937825202942,
+      "learning_rate": 0.0001,
+      "loss": 0.2236,
+      "step": 250
+    },
+    {
+      "epoch": 2.5060240963855422,
+      "grad_norm": 0.201055645942688,
+      "learning_rate": 0.0001,
+      "loss": 0.2184,
+      "step": 260
+    },
+    {
+      "epoch": 2.602409638554217,
+      "grad_norm": 0.17147445678710938,
+      "learning_rate": 0.0001,
+      "loss": 0.2205,
+      "step": 270
+    },
+    {
+      "epoch": 2.6987951807228914,
+      "grad_norm": 0.12793570756912231,
+      "learning_rate": 0.0001,
+      "loss": 0.2146,
+      "step": 280
+    },
+    {
+      "epoch": 2.7951807228915664,
+      "grad_norm": 0.18070928752422333,
+      "learning_rate": 0.0001,
+      "loss": 0.2163,
+      "step": 290
+    },
+    {
+      "epoch": 2.891566265060241,
+      "grad_norm": 0.1529516875743866,
+      "learning_rate": 0.0001,
+      "loss": 0.216,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -96,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5158452580270080.0,
+  "total_flos": 1.547183001305088e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null