Upload fine-tuned model

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb02ad71b42dd7868e306f5c52b8147bbbc4ffe587431064c483431bd453a42
+size 2510808826

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af5675aea048e7cf2719f0e9dbaaff28dd31f3a936396127f0bd926a2819b2b
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cacb2b573ef2420583c8e8cfb1b74875c1966226935d8b0b17beb98088ca76b
+size 1064

trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8484848484848486,
+  "eval_steps": 25,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 7.2911,
+      "step": 2
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 7.4303,
+      "step": 4
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 7.6339,
+      "step": 6
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2790.657958984375,
+      "learning_rate": 0.0,
+      "loss": 7.5141,
+      "step": 8
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 2633.2626953125,
+      "learning_rate": 4e-08,
+      "loss": 7.2612,
+      "step": 10
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 2636.133544921875,
+      "learning_rate": 8e-08,
+      "loss": 6.5574,
+      "step": 12
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 1873.4625244140625,
+      "learning_rate": 1.2e-07,
+      "loss": 5.1265,
+      "step": 14
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 564.6832885742188,
+      "learning_rate": 1.6e-07,
+      "loss": 2.4675,
+      "step": 16
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 105.86552429199219,
+      "learning_rate": 2e-07,
+      "loss": 0.5371,
+      "step": 18
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 26.96341896057129,
+      "learning_rate": 1.9863613034027222e-07,
+      "loss": 0.4874,
+      "step": 20
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 13.305822372436523,
+      "learning_rate": 1.9458172417006346e-07,
+      "loss": 0.3765,
+      "step": 22
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 10.41936206817627,
+      "learning_rate": 1.8794737512064888e-07,
+      "loss": 0.3488,
+      "step": 24
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "eval_loss": 0.16974905133247375,
+      "eval_runtime": 1.2389,
+      "eval_samples_per_second": 24.216,
+      "eval_steps_per_second": 8.072,
+      "step": 25
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 10.6868314743042,
+      "learning_rate": 1.7891405093963936e-07,
+      "loss": 0.4077,
+      "step": 26
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 9.373716354370117,
+      "learning_rate": 1.6772815716257412e-07,
+      "loss": 0.3063,
+      "step": 28
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 8.82962417602539,
+      "learning_rate": 1.546948158122427e-07,
+      "loss": 0.3607,
+      "step": 30
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 12.378520011901855,
+      "learning_rate": 1.4016954246529695e-07,
+      "loss": 0.3643,
+      "step": 32
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.897531509399414,
+      "learning_rate": 1.2454854871407992e-07,
+      "loss": 0.3154,
+      "step": 34
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 9.431836128234863,
+      "learning_rate": 1.0825793454723325e-07,
+      "loss": 0.3665,
+      "step": 36
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 8.315269470214844,
+      "learning_rate": 9.174206545276677e-08,
+      "loss": 0.3051,
+      "step": 38
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 8.550719261169434,
+      "learning_rate": 7.545145128592009e-08,
+      "loss": 0.2703,
+      "step": 40
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 9.788152694702148,
+      "learning_rate": 5.983045753470308e-08,
+      "loss": 0.3073,
+      "step": 42
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 9.642581939697266,
+      "learning_rate": 4.530518418775733e-08,
+      "loss": 0.328,
+      "step": 44
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 8.785964965820312,
+      "learning_rate": 3.227184283742591e-08,
+      "loss": 0.2671,
+      "step": 46
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 8.737689018249512,
+      "learning_rate": 2.108594906036065e-08,
+      "loss": 0.3968,
+      "step": 48
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 48,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1674122719395840.0,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}