Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b67e41ed00d2988f2a953732e3cea60fbca1c8978b56b795619d682c8546e07
+size 1442699

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fce6752ecbb6604e085ca1097f9b912b27b72a35695df4d7aa7a7834acef80
+size 499774435

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799c2a9b233aca9b1649a975d8fc2d128798bc9a26769fb0f6cf72a67c9a46d2
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e9f7fe1ab29af6aa77e6004c57876d5313c9d3da26e9e11a0acfa75ab42122
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fff2ccf7c72f15d3b76ddb019c26a4dca9d2e1f2ee32840db12f9fec2b95bea
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a4e867fa1241d92d6bcf27766baa9f317570cbfb999ddb76e020d43ec7d4dc
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4acf2b09a1339e370773a0fd0c75b1d5891aee4c56e1dd818e17f835520caf
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7546ae9c1e6fa6e6426b888392672f7514267f83e14e93ef8fc7db13a5220a3b
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f84e63e29d923cc8c21554fe213de1a06f00b47198b99fe493dcf59f2ace055
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b48f05a6fe6d1fbe948bd035323503b6cde575c8bc475d73338ea1f2101f32e
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b716fb1dcbc77ddc6a0ae7c4c98d559e36f1986fff006ef6982bd75247833235
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 17.168848037719727,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 67.9955,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 17.03850555419922,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 54.2312,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 14.042399406433105,
+      "learning_rate": 0.00023920000000000001,
+      "loss": 51.6192,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 27.294328689575195,
+      "learning_rate": 0.0003192,
+      "loss": 50.0348,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 24.557180404663086,
+      "learning_rate": 0.0003992,
+      "loss": 48.6163,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 16.080244064331055,
+      "learning_rate": 0.00047920000000000005,
+      "loss": 47.19,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 11.565583229064941,
+      "learning_rate": 0.0005592,
+      "loss": 46.5522,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 20.977285385131836,
+      "learning_rate": 0.0006392,
+      "loss": 46.0124,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 27.219560623168945,
+      "learning_rate": 0.0007191999999999999,
+      "loss": 45.5052,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 15.375182151794434,
+      "learning_rate": 0.0007992,
+      "loss": 44.7058,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.18614285714285714,
+      "eval_loss": 44.36890411376953,
+      "eval_runtime": 14.8109,
+      "eval_samples_per_second": 8.44,
+      "eval_steps_per_second": 0.135,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 14.803359031677246,
+      "learning_rate": 0.0008792,
+      "loss": 44.1071,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 9.71738338470459,
+      "learning_rate": 0.0009592000000000001,
+      "loss": 43.516,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 14.85153865814209,
+      "learning_rate": 0.0010391999999999999,
+      "loss": 42.9438,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 7.095604419708252,
+      "learning_rate": 0.0011192,
+      "loss": 42.2365,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.978736400604248,
+      "learning_rate": 0.0011992,
+      "loss": 41.832,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 7.7359161376953125,
+      "learning_rate": 0.0012791999999999999,
+      "loss": 42.4716,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 6.965914726257324,
+      "learning_rate": 0.0013592,
+      "loss": 41.8079,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 7.237981796264648,
+      "learning_rate": 0.0014392,
+      "loss": 41.2717,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 6.8691253662109375,
+      "learning_rate": 0.0015192,
+      "loss": 40.9756,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 9.182296752929688,
+      "learning_rate": 0.0015992,
+      "loss": 40.5064,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.2189471624266145,
+      "eval_loss": 40.17017364501953,
+      "eval_runtime": 3.4954,
+      "eval_samples_per_second": 35.761,
+      "eval_steps_per_second": 0.572,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b7158ace9259ba4a46b6e596e8ae3278650c23f403ecbb51a56d4d4d36529b
+size 5905