Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290d3415f88d0aa6d2afc82b9cd5f52a66da76a1b8dcef2153a477c366098b63
+size 1442699

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fe97d8864d635e74e59a243935c32329fbca3a7eff55bcfa48502a005f0d95
+size 499774435

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: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": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002,
+      "grad_norm": 2.427967071533203,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 8.595370483398437,
+      "step": 100
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 2.0173449516296387,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 6.985690307617188,
+      "step": 200
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 2.1842076778411865,
+      "learning_rate": 0.00023920000000000001,
+      "loss": 6.733137817382812,
+      "step": 300
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 1.4833307266235352,
+      "learning_rate": 0.0003192,
+      "loss": 6.513255004882812,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.232273578643799,
+      "learning_rate": 0.0003992,
+      "loss": 6.504192504882813,
+      "step": 500
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.256459951400757,
+      "learning_rate": 0.00047920000000000005,
+      "loss": 6.356998901367188,
+      "step": 600
+    },
+    {
+      "epoch": 0.014,
+      "grad_norm": 1.6759421825408936,
+      "learning_rate": 0.0005592,
+      "loss": 6.304365234375,
+      "step": 700
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 1.164450764656067,
+      "learning_rate": 0.0006392,
+      "loss": 6.234349975585937,
+      "step": 800
+    },
+    {
+      "epoch": 0.018,
+      "grad_norm": 2.5291967391967773,
+      "learning_rate": 0.0007191999999999999,
+      "loss": 6.173318481445312,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1007851362228394,
+      "learning_rate": 0.0007992,
+      "loss": 6.1113330078125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.14623679060665362,
+      "eval_loss": 6.150835037231445,
+      "eval_runtime": 13.1402,
+      "eval_samples_per_second": 76.102,
+      "eval_steps_per_second": 9.513,
+      "step": 1000
+    },
+    {
+      "epoch": 0.022,
+      "grad_norm": 0.8226528167724609,
+      "learning_rate": 0.0008792,
+      "loss": 6.04904052734375,
+      "step": 1100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.1409642696380615,
+      "learning_rate": 0.0009592000000000001,
+      "loss": 5.977291259765625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.026,
+      "grad_norm": 0.9230883121490479,
+      "learning_rate": 0.0010391999999999999,
+      "loss": 5.983433837890625,
+      "step": 1300
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.7991492748260498,
+      "learning_rate": 0.0011192,
+      "loss": 5.960853271484375,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9952593445777893,
+      "learning_rate": 0.0011992,
+      "loss": 5.900661010742187,
+      "step": 1500
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 2.6635053157806396,
+      "learning_rate": 0.0012791999999999999,
+      "loss": 5.839690551757813,
+      "step": 1600
+    },
+    {
+      "epoch": 0.034,
+      "grad_norm": 0.7056213021278381,
+      "learning_rate": 0.0013592,
+      "loss": 5.864632568359375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.7523426413536072,
+      "learning_rate": 0.0014392,
+      "loss": 5.8030767822265625,
+      "step": 1800
+    },
+    {
+      "epoch": 0.038,
+      "grad_norm": 0.572576105594635,
+      "learning_rate": 0.0015192,
+      "loss": 5.829718017578125,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8802671432495117,
+      "learning_rate": 0.0015992,
+      "loss": 5.767376098632813,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.163426614481409,
+      "eval_loss": 5.823215484619141,
+      "eval_runtime": 6.7868,
+      "eval_samples_per_second": 147.345,
+      "eval_steps_per_second": 18.418,
+      "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 sha256:171dcca5dd485fdeb3004467beb89d527c3e1a4b53ac71d60e64c0c223983b09
+size 5329