Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29c2ac56ecaf890183c92f0429f6f4ac21c273e2137eb84c857497b085b0c42
+size 386699

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7cf547fc97b89807cf1b0e9421d844cd92670b12240a099a4ff9cca25b9217
+size 1540661735

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8b5a6f3b4365ce554cba583f0313d64f584f30a62aae6a4e6bcb915469a7c0
+size 14455

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 +1,113 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": NaN,
+      "learning_rate": 0.0003973800426880847,
+      "loss": NaN,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": NaN,
+      "learning_rate": 0.0003762085737488283,
+      "loss": NaN,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": NaN,
+      "learning_rate": 0.00033594217168615465,
+      "loss": NaN,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": NaN,
+      "learning_rate": 0.00028094432596115747,
+      "loss": NaN,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": NaN,
+      "learning_rate": 0.00021717490653764342,
+      "loss": NaN,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015154431949464275,
+      "loss": NaN,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": NaN,
+      "learning_rate": 9.11646573017482e-05,
+      "loss": NaN,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": NaN,
+      "learning_rate": 4.2578993244549506e-05,
+      "loss": NaN,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": NaN,
+      "learning_rate": 1.1052337907897503e-05,
+      "loss": NaN,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 1.093583978573065e-09,
+      "loss": NaN,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0010862745098039217,
+      "eval_loss": NaN,
+      "eval_runtime": 23.4851,
+      "eval_samples_per_second": 42.58,
+      "eval_steps_per_second": 21.29,
+      "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788a46a9479bd41d71f654f74298a4024e4f78c6eec0ebca50a7680be9e34c43
+size 5329