Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e9de8cc6a482a3ed5dfac318ef71ee255f03bf725794427f3c5f1bbd9f7f6d
+size 2610104820

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d896fd4f946fa2f0f2a26453099a100914499a2112b9e42e53eba2979f7c71af
+size 5210004271

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35b4cd4104958a3e34a87e84eee852763c80157fefbeae8abd4d6ed6ea94168
+size 15006

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca4dbe650e04bc8012dd3f1938dfb2a637329721abd75c3bd59d28a64007b54
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 1.202221393585205,
+  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 129,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3904343582235237,
+      "grad_norm": 0.15374162793159485,
+      "learning_rate": 9.609375e-05,
+      "loss": 1.3304,
+      "step": 50
+    },
+    {
+      "epoch": 0.3904343582235237,
+      "eval_loss": 1.2847646474838257,
+      "eval_runtime": 10.2922,
+      "eval_samples_per_second": 41.973,
+      "eval_steps_per_second": 20.987,
+      "step": 50
+    },
+    {
+      "epoch": 0.7808687164470474,
+      "grad_norm": 0.2127045840024948,
+      "learning_rate": 9.21875e-05,
+      "loss": 1.2406,
+      "step": 100
+    },
+    {
+      "epoch": 0.7808687164470474,
+      "eval_loss": 1.202221393585205,
+      "eval_runtime": 10.2918,
+      "eval_samples_per_second": 41.975,
+      "eval_steps_per_second": 20.988,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "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": 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 sha256:7d856b67d33930594c96488b6dfefca1df3605d069986e287eeb88373a9df91b
+size 5368