Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c06d3ba466680d20e83dca1f72ae896e45012b2aac10f1213573e33e369131a
+size 847599616

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f5c15366758b9c7691ee7b8a10e03f333fe2133f38def1a5ebad01ed824459
+size 350603

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93ec8d96aaa0c43a5a884ca6c90a318c00f4af0168b05a46c3f804d3a01bf7d
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1,
+  "eval_steps": 20,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.19855035841464996,
+      "learning_rate": 1.6e-06,
+      "loss": 22.03577117919922,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.20424452424049377,
+      "learning_rate": 3.6e-06,
+      "loss": 22.039888000488283,
+      "step": 10
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.19867758452892303,
+      "learning_rate": 3.995627254437549e-06,
+      "loss": 22.05139923095703,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.21107740700244904,
+      "learning_rate": 3.9778957412029366e-06,
+      "loss": 22.04059600830078,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 1.978021978021978e-05,
+      "eval_loss": 11.020455360412598,
+      "eval_runtime": 92.6203,
+      "eval_samples_per_second": 10.797,
+      "eval_steps_per_second": 2.699,
+      "step": 20
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 20,
+  "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:ff6acc2c85619ab487b0f5352ddad26b9a9f05dd3dec11fa8ed4abb1a5a9ef99
+size 5265