Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d69a236e68b6332db7d3cff5deaa06ec25ff0e5efa550677ce2f35df088680
+size 386379

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6bc441453e9b4734e133be3c600607e5b3dee32b860836792368241f27642d
+size 1540661735

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43badff6712b33504459f872ac58be74afdf5ffa731e863439dbed8d3f3b0658
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12eac59d8227e48f0e6fc2526645da1f69a0138bb2904859d6e0d18216ba63d7
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c12b9a050992357585c15ce67795abc69719e584223ec4ccbae89612840d277
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da83cd5eef961d44e4becc44e4089edf261063947ef5a08e30404cfbd611e2c3
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd920f545c0711cea231c43d68bcba64df0cc8fd9e536bc95aea4ceced55b64
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e310e83ca23aa2c5186dec200b69809f8eb565d4f17f262d28f343cd531776
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67aa5039be38b0a461bcbf305aaf4eb5ca5764f1670f75af2089e433b412f3af
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c15db3462043815a7b702c6ec5d03f93688f7392547928696d4f1b5bc14356
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31938cdcda9330861d9a6c5fa22f1c1b3736037ca4758e7ec127110a6ee0d1a
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16666666666666666,
+  "eval_steps": 250,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 1325.952880859375,
+      "learning_rate": 0.00013066666666666668,
+      "loss": 1512.93171875,
+      "step": 50
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 929.898681640625,
+      "learning_rate": 0.000264,
+      "loss": 1464.5940625,
+      "step": 100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 747.4642333984375,
+      "learning_rate": 0.00039733333333333336,
+      "loss": 1415.48578125,
+      "step": 150
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 631.6712646484375,
+      "learning_rate": 0.000399708326752494,
+      "loss": 1384.57703125,
+      "step": 200
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 805.9771728515625,
+      "learning_rate": 0.0003988102673898103,
+      "loss": 1370.675,
+      "step": 250
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "eval_accuracy": 0.18672140762463343,
+      "eval_loss": 45.42939758300781,
+      "eval_runtime": 25.5972,
+      "eval_samples_per_second": 4.883,
+      "eval_steps_per_second": 0.156,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 653.5927124023438,
+      "learning_rate": 0.00039730842777928766,
+      "loss": 1365.14890625,
+      "step": 300
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 995.5695190429688,
+      "learning_rate": 0.0003952073689584629,
+      "loss": 1359.084375,
+      "step": 350
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 825.2788696289062,
+      "learning_rate": 0.00039251347177392016,
+      "loss": 1355.68390625,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 615.8878784179688,
+      "learning_rate": 0.00038923491750286954,
+      "loss": 1353.1375,
+      "step": 450
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 895.9261474609375,
+      "learning_rate": 0.00038538166300687717,
+      "loss": 1349.4459375,
+      "step": 500
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "eval_accuracy": 0.19390224828934507,
+      "eval_loss": 44.819725036621094,
+      "eval_runtime": 7.3949,
+      "eval_samples_per_second": 16.904,
+      "eval_steps_per_second": 0.541,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3000,
+  "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": 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:cdf1bf7ff316b803830588f07fd42e9d70dbb919d664b54789baf8adc99f17cf
+size 5265