Upload folder using huggingface_hub

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8d8a19f74dd66c17af1dc62a029467825edbf7ddc03d6a189216f9b4eb83c8
+oid sha256:8ba541ec704c2be4990f2a4e785680effcaf8d143b10ea9a0f2a33cc4f52366a
 size 4918393736

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51db9ad85bf295140e2ebe478fa1169eee63ec17ecd27723ac4cd0a63077e38
+size 7520226

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f800f82626834898f42b7f9c69003dfc04c36a0245d8b94f9de3dece5b3549a4
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06519fc6224388883e936edd74785948027c1b3c30d6c40dea934e196b4e8bc4
+size 1064

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6879999999999997,
+  "eval_steps": 500,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.9510765075683594,
+      "learning_rate": 3e-05,
+      "loss": 0.3941,
+      "step": 1
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.0055848360061646,
+      "learning_rate": 3e-05,
+      "loss": 0.192,
+      "step": 2
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 1.002354383468628,
+      "learning_rate": 3e-05,
+      "loss": 0.258,
+      "step": 3
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.0138096809387207,
+      "learning_rate": 3e-05,
+      "loss": 0.2067,
+      "step": 4
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2955703735351562,
+      "learning_rate": 3e-05,
+      "loss": 0.1766,
+      "step": 5
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.8161090612411499,
+      "learning_rate": 3e-05,
+      "loss": 0.235,
+      "step": 6
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.9679957628250122,
+      "learning_rate": 3e-05,
+      "loss": 0.2382,
+      "step": 7
+    },
+    {
+      "epoch": 0.896,
+      "eval_loss": 0.16826605796813965,
+      "eval_runtime": 63.1414,
+      "eval_samples_per_second": 72.472,
+      "eval_steps_per_second": 18.118,
+      "step": 7
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 1.012323021888733,
+      "learning_rate": 3e-05,
+      "loss": 0.1784,
+      "step": 8
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.7350760698318481,
+      "learning_rate": 3e-05,
+      "loss": 0.1419,
+      "step": 9
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.0166149139404297,
+      "learning_rate": 3e-05,
+      "loss": 0.1867,
+      "step": 10
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4892595708370209,
+      "learning_rate": 3e-05,
+      "loss": 0.0947,
+      "step": 11
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.9143627882003784,
+      "learning_rate": 3e-05,
+      "loss": 0.1689,
+      "step": 12
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 2.587285280227661,
+      "learning_rate": 3e-05,
+      "loss": 0.166,
+      "step": 13
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.7984355688095093,
+      "learning_rate": 3e-05,
+      "loss": 0.1384,
+      "step": 14
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7720908522605896,
+      "learning_rate": 3e-05,
+      "loss": 0.1573,
+      "step": 15
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.1329023391008377,
+      "eval_runtime": 62.0834,
+      "eval_samples_per_second": 73.707,
+      "eval_steps_per_second": 18.427,
+      "step": 15
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8049373030662537,
+      "learning_rate": 3e-05,
+      "loss": 0.1272,
+      "step": 16
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.6391154527664185,
+      "learning_rate": 3e-05,
+      "loss": 0.1067,
+      "step": 17
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.43653327226638794,
+      "learning_rate": 3e-05,
+      "loss": 0.0935,
+      "step": 18
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6862492561340332,
+      "learning_rate": 3e-05,
+      "loss": 0.1373,
+      "step": 19
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.5739763975143433,
+      "learning_rate": 3e-05,
+      "loss": 0.0933,
+      "step": 20
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.4819794297218323,
+      "learning_rate": 3e-05,
+      "loss": 0.0796,
+      "step": 21
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "eval_loss": 0.11852595210075378,
+      "eval_runtime": 60.9297,
+      "eval_samples_per_second": 75.103,
+      "eval_steps_per_second": 18.776,
+      "step": 21
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 21,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1414126220083200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}