Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5805072dd72dbaa444aa95ea79904fe117bd9e08603dd8903d889b35eb5d72c
+size 386379

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b50dc3b8d7f6527e6deb35523fc5f4f66de87b59bae32d7b673859cc29de173
+size 1540661735

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffdf794aa37bf66c11fbf3a25c5c6e95b77bf37b30e60af016fc9124d0bcb99
+size 14469

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81af6df700759cf275cafea0cdaf381ba3c2b41fab7e7379341c665c147ed0de
+size 14469

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55b42bedc0f28bff9c30b7bebe80ce64a5aa5c0c36daab2e46abff72980db18
+size 14469

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef44384c481d885f2114df6c79173cd8acc16cb1ee47046bf46031abdcc9c81b
+size 14469

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41a4b4c8c4b93050c780cbd4537fecb50bacfb6229c463432858be6d6a803f6
+size 14469

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79aee2c3afea7ec6ffe3ac7b43481b7334a7abba51e0d4f2ed2312cd5550aeb
+size 14469

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c918f0602d1108574e113fb8e32d725731b2c86339c03552c0229840eb091bf8
+size 14469

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f462384e1628ac3068742a9ce939fc67956eb63350336c85c9bc3aee27af07
+size 14469

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f532a77c9963a928cf7277c87e919c365cd36b1e11776f70173ba96ec9da717
+size 1465

last-checkpoint/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": false,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0159783363342285,
+      "learning_rate": 0.003920764340590609,
+      "loss": 67.322138671875,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.1363150684931507,
+      "eval_loss": 62.45854568481445,
+      "eval_runtime": 15.2216,
+      "eval_samples_per_second": 8.212,
+      "eval_steps_per_second": 0.263,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.178174614906311,
+      "learning_rate": 0.003650943793925548,
+      "loss": 60.51267578125,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.14354794520547945,
+      "eval_loss": 59.48474884033203,
+      "eval_runtime": 3.1576,
+      "eval_samples_per_second": 39.587,
+      "eval_steps_per_second": 1.267,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9601056575775146,
+      "learning_rate": 0.0032162636906540357,
+      "loss": 58.783408203125,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.14687671232876712,
+      "eval_loss": 58.058326721191406,
+      "eval_runtime": 3.3957,
+      "eval_samples_per_second": 36.812,
+      "eval_steps_per_second": 1.178,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6054814457893372,
+      "learning_rate": 0.0026601302141692667,
+      "loss": 57.62333984375,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.1496399217221135,
+      "eval_loss": 57.01893615722656,
+      "eval_runtime": 3.9547,
+      "eval_samples_per_second": 31.608,
+      "eval_steps_per_second": 1.011,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.638672411441803,
+      "learning_rate": 0.002038077610206693,
+      "loss": 56.62125,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.151720156555773,
+      "eval_loss": 56.300567626953125,
+      "eval_runtime": 3.3169,
+      "eval_samples_per_second": 37.686,
+      "eval_steps_per_second": 1.206,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "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 sha256:4ca316f954a0e91646cfe7cc48ead82990c29283d2e6825936de0377c3707c2e
+size 5265