Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f4e73a7428807d0545ea63e75cb228396f0cccd6fbcd5ae2eaf2557ecae994
+size 1417163

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc861cf9df458b75f1604d94b61feea15513b6ffde8bb6828abb654c32ba1ea8
+size 292928643

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cfd50ff3a42065a545f46e5e0d163da023498a41ad02da368f633d32b47d2c
+size 14455

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc933910f13fa41b7f95dbbbc23336663568ef33e75bf367c77b2082bd938180
+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": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 14.826459884643555,
+      "learning_rate": 7.920000000000001e-07,
+      "loss": 10.879287109375,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 17.237497329711914,
+      "learning_rate": 1.5920000000000002e-06,
+      "loss": 10.74796630859375,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 5.412790298461914,
+      "learning_rate": 2.392e-06,
+      "loss": 10.419390869140624,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 3.887077569961548,
+      "learning_rate": 3.192e-06,
+      "loss": 10.083310546875,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.948329448699951,
+      "learning_rate": 3.992e-06,
+      "loss": 9.929519653320312,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 3.4345157146453857,
+      "learning_rate": 4.792000000000001e-06,
+      "loss": 9.777420654296876,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 4.727835655212402,
+      "learning_rate": 5.592000000000001e-06,
+      "loss": 9.646694946289063,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 2.9691734313964844,
+      "learning_rate": 6.392000000000001e-06,
+      "loss": 9.485365600585938,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 8.859844207763672,
+      "learning_rate": 7.192e-06,
+      "loss": 9.32474365234375,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.142549514770508,
+      "learning_rate": 7.992e-06,
+      "loss": 9.14423828125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.09021526418786693,
+      "eval_loss": 9.03640079498291,
+      "eval_runtime": 20.6098,
+      "eval_samples_per_second": 48.521,
+      "eval_steps_per_second": 6.065,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 6.929040431976318,
+      "learning_rate": 8.792e-06,
+      "loss": 8.938278198242188,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 3.2667243480682373,
+      "learning_rate": 9.592e-06,
+      "loss": 8.691138916015625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 3.8360178470611572,
+      "learning_rate": 1.0392e-05,
+      "loss": 8.525877685546876,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 7.723220348358154,
+      "learning_rate": 1.1192e-05,
+      "loss": 8.324917602539063,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.095365047454834,
+      "learning_rate": 1.1992000000000001e-05,
+      "loss": 8.129039916992188,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 8.2203950881958,
+      "learning_rate": 1.2792e-05,
+      "loss": 7.922721557617187,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 3.7490456104278564,
+      "learning_rate": 1.3592000000000001e-05,
+      "loss": 7.799203491210937,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 4.54710054397583,
+      "learning_rate": 1.4392000000000002e-05,
+      "loss": 7.621753540039062,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 2.902744770050049,
+      "learning_rate": 1.5192000000000003e-05,
+      "loss": 7.5074224853515625,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.133886337280273,
+      "learning_rate": 1.5992000000000002e-05,
+      "loss": 7.375697631835937,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.1294050880626223,
+      "eval_loss": 7.383677959442139,
+      "eval_runtime": 7.6198,
+      "eval_samples_per_second": 131.237,
+      "eval_steps_per_second": 16.405,
+      "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 sha256:0551fcc809086177b55c2e14e6be9041103a4dee9033ded1a7be27d9690e908d
+size 5329