Upload 12 files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52286912af34524b209dbbc246202e5dcc8e24de07def3f2d33ba30f0bcf5475
+oid sha256:3d4ddf2ce5e52785e159bb543cfc5d13a46b48436c6996da4d5850b10dc6ee63
 size 307867048

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0d4c24253a37cd608f7598eebea2731e51a7aa7d7430dc913e8e5dc42a8cba
+size 615844491

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd431d82edbf5bd9b9521c3f6b545b4bc130b9fd64942c06605d68ca9a240097
+size 14391

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad0c2ffc405a73a0d15ee1b8345e05770d3bcdba1693ebf4d5b02e702c243b
+size 1465

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 90.42544555664062,
+      "learning_rate": 4.9e-05,
+      "loss": 37.9627,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 94.14350891113281,
+      "learning_rate": 4.8e-05,
+      "loss": 31.6371,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 91.6609878540039,
+      "learning_rate": 4.7e-05,
+      "loss": 25.7576,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 79.74266815185547,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 20.5862,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 72.54832458496094,
+      "learning_rate": 4.5e-05,
+      "loss": 15.9883,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 41.900142669677734,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 11.2606,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 25.399627685546875,
+      "learning_rate": 4.3e-05,
+      "loss": 8.4267,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 23.45610237121582,
+      "learning_rate": 4.2e-05,
+      "loss": 7.1794,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 24.75299644470215,
+      "learning_rate": 4.1e-05,
+      "loss": 6.2873,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.834659576416016,
+      "learning_rate": 4e-05,
+      "loss": 5.5835,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 21.57811737060547,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 4.9805,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 20.588825225830078,
+      "learning_rate": 3.8e-05,
+      "loss": 4.6298,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 19.950162887573242,
+      "learning_rate": 3.7e-05,
+      "loss": 4.2783,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 22.45453643798828,
+      "learning_rate": 3.6e-05,
+      "loss": 4.0239,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 23.211528778076172,
+      "learning_rate": 3.5e-05,
+      "loss": 3.7593,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 22.85753059387207,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 3.5531,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 24.395389556884766,
+      "learning_rate": 3.3e-05,
+      "loss": 3.313,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 24.141725540161133,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 3.1407,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 24.2203311920166,
+      "learning_rate": 3.1e-05,
+      "loss": 2.9579,
+      "step": 190
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 25.553144454956055,
+      "learning_rate": 3e-05,
+      "loss": 2.7774,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 26.164714813232422,
+      "learning_rate": 2.9e-05,
+      "loss": 2.5997,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 25.814773559570312,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.4666,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 26.79621124267578,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 2.3196,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 25.93185043334961,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.1519,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.01556396484375,
+      "learning_rate": 2.5e-05,
+      "loss": 2.0465,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 185890504704000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}