Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef173a39c7444de07068474450f487f3f7ada15660d4514110e0b8caf6b8238d
+oid sha256:e7199032c0bb48f4e3f23675b3a1c970189d67c15cf1579dd23df3488b0b3e3a
 size 1852600

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fe1bcbf22a34222feeabd157ef29f7b3cb2ec9206af80fc10023f9386bae86
+size 1108346

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d953226bc417945899e87f53a6081640f34a8b71d67a0b1cf564824efa9463
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e95e5f44861e8059ee6a3a64cda7d8ed399274b958454ac1793d881fa8c44c
+size 1064

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4405125076266017,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09762050030506407,
+      "grad_norm": 0.8231198191642761,
+      "learning_rate": 4e-05,
+      "loss": 2.624,
+      "step": 20
+    },
+    {
+      "epoch": 0.19524100061012814,
+      "grad_norm": 1.040634274482727,
+      "learning_rate": 8e-05,
+      "loss": 2.5599,
+      "step": 40
+    },
+    {
+      "epoch": 0.2928615009151922,
+      "grad_norm": 1.0133676528930664,
+      "learning_rate": 0.00012,
+      "loss": 2.1985,
+      "step": 60
+    },
+    {
+      "epoch": 0.3904820012202563,
+      "grad_norm": 1.0250593423843384,
+      "learning_rate": 0.00016,
+      "loss": 1.9481,
+      "step": 80
+    },
+    {
+      "epoch": 0.4881025015253203,
+      "grad_norm": 0.9968363046646118,
+      "learning_rate": 0.0002,
+      "loss": 1.7738,
+      "step": 100
+    },
+    {
+      "epoch": 0.5857230018303844,
+      "grad_norm": 1.4279309511184692,
+      "learning_rate": 0.0001998688524590164,
+      "loss": 1.7329,
+      "step": 120
+    },
+    {
+      "epoch": 0.6833435021354485,
+      "grad_norm": 1.3037158250808716,
+      "learning_rate": 0.0001997377049180328,
+      "loss": 1.6784,
+      "step": 140
+    },
+    {
+      "epoch": 0.7809640024405126,
+      "grad_norm": 1.404618263244629,
+      "learning_rate": 0.00019960655737704918,
+      "loss": 1.6264,
+      "step": 160
+    },
+    {
+      "epoch": 0.8785845027455765,
+      "grad_norm": 1.058852195739746,
+      "learning_rate": 0.0001994754098360656,
+      "loss": 1.6077,
+      "step": 180
+    },
+    {
+      "epoch": 0.9762050030506406,
+      "grad_norm": 1.8023818731307983,
+      "learning_rate": 0.00019934426229508198,
+      "loss": 1.5252,
+      "step": 200
+    },
+    {
+      "epoch": 1.0738255033557047,
+      "grad_norm": 1.2388545274734497,
+      "learning_rate": 0.00019921311475409837,
+      "loss": 1.5621,
+      "step": 220
+    },
+    {
+      "epoch": 1.1714460036607688,
+      "grad_norm": 1.5438932180404663,
+      "learning_rate": 0.00019908196721311476,
+      "loss": 1.4877,
+      "step": 240
+    },
+    {
+      "epoch": 1.2690665039658329,
+      "grad_norm": 1.590529203414917,
+      "learning_rate": 0.00019895081967213115,
+      "loss": 1.5568,
+      "step": 260
+    },
+    {
+      "epoch": 1.366687004270897,
+      "grad_norm": 1.2864124774932861,
+      "learning_rate": 0.00019881967213114757,
+      "loss": 1.5082,
+      "step": 280
+    },
+    {
+      "epoch": 1.4643075045759608,
+      "grad_norm": 1.4031420946121216,
+      "learning_rate": 0.00019868852459016393,
+      "loss": 1.467,
+      "step": 300
+    },
+    {
+      "epoch": 1.561928004881025,
+      "grad_norm": 1.5916552543640137,
+      "learning_rate": 0.00019855737704918035,
+      "loss": 1.4055,
+      "step": 320
+    },
+    {
+      "epoch": 1.659548505186089,
+      "grad_norm": 1.5989781618118286,
+      "learning_rate": 0.00019842622950819674,
+      "loss": 1.358,
+      "step": 340
+    },
+    {
+      "epoch": 1.757169005491153,
+      "grad_norm": 1.7474373579025269,
+      "learning_rate": 0.00019829508196721313,
+      "loss": 1.3905,
+      "step": 360
+    },
+    {
+      "epoch": 1.8547895057962172,
+      "grad_norm": 1.8275643587112427,
+      "learning_rate": 0.00019816393442622951,
+      "loss": 1.4449,
+      "step": 380
+    },
+    {
+      "epoch": 1.9524100061012812,
+      "grad_norm": 1.7919280529022217,
+      "learning_rate": 0.0001980327868852459,
+      "loss": 1.4057,
+      "step": 400
+    },
+    {
+      "epoch": 2.0500305064063453,
+      "grad_norm": 2.0150179862976074,
+      "learning_rate": 0.00019790163934426232,
+      "loss": 1.3659,
+      "step": 420
+    },
+    {
+      "epoch": 2.1476510067114094,
+      "grad_norm": 2.0520079135894775,
+      "learning_rate": 0.00019777049180327868,
+      "loss": 1.3735,
+      "step": 440
+    },
+    {
+      "epoch": 2.2452715070164735,
+      "grad_norm": 2.1597766876220703,
+      "learning_rate": 0.0001976393442622951,
+      "loss": 1.318,
+      "step": 460
+    },
+    {
+      "epoch": 2.3428920073215376,
+      "grad_norm": 1.8374860286712646,
+      "learning_rate": 0.0001975081967213115,
+      "loss": 1.3469,
+      "step": 480
+    },
+    {
+      "epoch": 2.4405125076266017,
+      "grad_norm": 2.2065134048461914,
+      "learning_rate": 0.00019737704918032788,
+      "loss": 1.3822,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 30600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6429114251698176.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}