Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a18eb66379b6698af86fb08013da4c523bb44e653fdb99cabf0ce326b80d22f
+size 386379

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e3a7767d132b2cee73f8c2a62b5f678a31e9a87e52b1878a4eb94b5ebeb94c
+size 1540661735

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daae0cc70f9e7824a39e0868e7bbd5f4ee69ddcba63b1d42d1220972622fb262
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b02a3ca08e76a328358ed359724403d0daf90280ad6996ccb99129eabd7933b
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881a4302f7ca452bf068ae4fa72a3351c17d2f02cc3ed78ed4d81d0440b092ef
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbad872a50b1b043373278688384873e9ce6d4b170a2b9147ea2e7045b6f08f
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5c33f86cd61c95af37958664568bdef66b045a7dd327e2e4a87418eb5c2617
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745adc34fef116335c62d35da815ab1e6c8444b933918aed8cd7d137cd7d3e67
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9873ce205beb3108aa535f93d98d3355954ff6b888a8d98df447b2c97fc448a
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992d5b22958331017a9e6fa5d52716b2c115acc308f2f7b00c82ee11a1c1b070
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b7b1a014f5dad743694fda5858015bfe3bd4c82eac608d649238b91858a560
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 12.30762004852295,
+      "learning_rate": 0.00039207643405906093,
+      "loss": 216.7740625,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.1816001955034213,
+      "eval_loss": 47.57754135131836,
+      "eval_runtime": 23.1275,
+      "eval_samples_per_second": 5.405,
+      "eval_steps_per_second": 0.173,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.95341968536377,
+      "learning_rate": 0.0003650943793925548,
+      "loss": 185.82048828125,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.19564027370478984,
+      "eval_loss": 45.45988082885742,
+      "eval_runtime": 7.2182,
+      "eval_samples_per_second": 17.317,
+      "eval_steps_per_second": 0.554,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9.293137550354004,
+      "learning_rate": 0.0003216263690654036,
+      "loss": 180.35142578125,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.2023049853372434,
+      "eval_loss": 44.628074645996094,
+      "eval_runtime": 7.037,
+      "eval_samples_per_second": 17.763,
+      "eval_steps_per_second": 0.568,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 9.892265319824219,
+      "learning_rate": 0.00026601302141692667,
+      "loss": 178.04525390625,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.20574193548387096,
+      "eval_loss": 44.19523239135742,
+      "eval_runtime": 7.0599,
+      "eval_samples_per_second": 17.706,
+      "eval_steps_per_second": 0.567,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.574827194213867,
+      "learning_rate": 0.00020380776102066933,
+      "loss": 176.7007421875,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.20855425219941348,
+      "eval_loss": 43.90693283081055,
+      "eval_runtime": 6.876,
+      "eval_samples_per_second": 18.179,
+      "eval_steps_per_second": 0.582,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 10.545783042907715,
+      "learning_rate": 0.00014122226612106885,
+      "loss": 175.240859375,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.2102414467253177,
+      "eval_loss": 43.72456741333008,
+      "eval_runtime": 6.9048,
+      "eval_samples_per_second": 18.103,
+      "eval_steps_per_second": 0.579,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.784721374511719,
+      "learning_rate": 8.450618433005866e-05,
+      "loss": 175.0915234375,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.2116852394916911,
+      "eval_loss": 43.59967803955078,
+      "eval_runtime": 6.9268,
+      "eval_samples_per_second": 18.046,
+      "eval_steps_per_second": 0.577,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.553999423980713,
+      "learning_rate": 3.932305678751549e-05,
+      "loss": 174.05962890625,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.21238318670576736,
+      "eval_loss": 43.53715515136719,
+      "eval_runtime": 6.7444,
+      "eval_samples_per_second": 18.534,
+      "eval_steps_per_second": 0.593,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 8.83249282836914,
+      "learning_rate": 1.0184769603774148e-05,
+      "loss": 174.92396484375,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.21264418377321603,
+      "eval_loss": 43.506919860839844,
+      "eval_runtime": 6.9005,
+      "eval_samples_per_second": 18.115,
+      "eval_steps_per_second": 0.58,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.517117500305176,
+      "learning_rate": 1.0069988897853933e-09,
+      "loss": 173.867734375,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.21278690127077224,
+      "eval_loss": 43.502532958984375,
+      "eval_runtime": 6.8719,
+      "eval_samples_per_second": 18.19,
+      "eval_steps_per_second": 0.582,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "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:e42ac3e5a09bb56fc92faab3744d893d5a5809db1bd4cadabb4c3a55653610d2
+size 5265