Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a54c527a33f70d78ce72260eeb46972b58e885b72ef3dfa0e6cc0f9688399f
+size 386379

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd76ca7ba0bf198b8ad479ccdd911afaab0648bdaf7b3f0f15806b98b32231d0
+size 1540661735

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21921ded89d3efb325b0f105635a2e638ac3849bf9d5ddc032cf285c7acce9df
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3ef5862d26b8869e6c9e8a6807701995c18e51a48f7f36ceda1b5abeed0909
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ffd59099867021edcfb0ac2baab041eb4a4af12f556bedc1ab80ec65d990ef
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e740bf1fa07b2703f88f14c6cf127f399fc76fbcdb55bc579c2b3e0e29cc02
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97342e1218bd168184eb81a3ba9ece8327ff8377151f7c84b89a8ad1cc5bf7ed
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402e70719eb092137380f0c146f2dd612f92092b503b35850f99d43e15b22645
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f39d1c0b40d5df607853ccb440ef174a83084d925f20ee2125e5030a6c85632
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcd028341979c2e359a61e18bb04bf5424e94e780cb8c2f9bc4ed21b1f02b37
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b79cc0df1e63ecef3adaaf8ef4c455eb58ccb70431c624030057057995b60a8
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.14088188976377952,
+      "eval_loss": 49.78975296020508,
+      "eval_runtime": 13.6275,
+      "eval_samples_per_second": 9.173,
+      "eval_steps_per_second": 1.174,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 13452.2255859375,
+      "learning_rate": 0.000264,
+      "loss": 1505.6178125,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.1445748031496063,
+      "eval_loss": 49.24732208251953,
+      "eval_runtime": 8.7677,
+      "eval_samples_per_second": 14.257,
+      "eval_steps_per_second": 1.825,
+      "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.1491968503937008,
+      "eval_loss": 48.760948181152344,
+      "eval_runtime": 8.1271,
+      "eval_samples_per_second": 15.381,
+      "eval_steps_per_second": 1.969,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8017.09326171875,
+      "learning_rate": 0.0003967291041791484,
+      "loss": 1469.6371875,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.15311023622047243,
+      "eval_loss": 48.39834213256836,
+      "eval_runtime": 8.3927,
+      "eval_samples_per_second": 14.894,
+      "eval_steps_per_second": 1.906,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.15462204724409448,
+      "eval_loss": 48.1512336730957,
+      "eval_runtime": 10.9865,
+      "eval_samples_per_second": 11.378,
+      "eval_steps_per_second": 1.456,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9418.4111328125,
+      "learning_rate": 0.0003704314025795668,
+      "loss": 1449.61,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.15623622047244096,
+      "eval_loss": 47.92970275878906,
+      "eval_runtime": 8.5559,
+      "eval_samples_per_second": 14.61,
+      "eval_steps_per_second": 1.87,
+      "step": 300
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.15805511811023623,
+      "eval_loss": 47.6953125,
+      "eval_runtime": 10.9375,
+      "eval_samples_per_second": 11.429,
+      "eval_steps_per_second": 1.463,
+      "step": 350
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3742.375,
+      "learning_rate": 0.0003211159956686115,
+      "loss": 1437.1715625,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.16048031496062992,
+      "eval_loss": 47.554046630859375,
+      "eval_runtime": 8.2976,
+      "eval_samples_per_second": 15.065,
+      "eval_steps_per_second": 1.928,
+      "step": 400
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.16221259842519686,
+      "eval_loss": 47.40172576904297,
+      "eval_runtime": 7.9017,
+      "eval_samples_per_second": 15.819,
+      "eval_steps_per_second": 2.025,
+      "step": 450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 12861.1259765625,
+      "learning_rate": 0.00025544320241571017,
+      "loss": 1426.95953125,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.1636220472440945,
+      "eval_loss": 47.27663803100586,
+      "eval_runtime": 8.5898,
+      "eval_samples_per_second": 14.552,
+      "eval_steps_per_second": 1.863,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "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": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247a6cb50101bbd16e7c8df652ac2c86b414e5a68a9035c7ff0bb74f21ee442f
+size 5265