Training in progress, step 150, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4ff4a862db7f46e931bc03ba272c34c8f1522376a8a2b406743dfb6aa5becd
+oid sha256:dfa17f31bad6f2f516b55fc5b26c3f0332bc8434cfdc669afe2a257fd5d49d26
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f1f0c8166dadba06fe6fc67f6066bed4cdb1ab73ea5aeb075d20803d8d6d3a
+oid sha256:eebc5675b2520100d7f6c4e7ae79cdf86ed8a10ff60e9eea536fab023e69d535
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4739482302d1b180f4028bb16db49eef68df7df979486c1d696295c50ea91e
+oid sha256:6625b6e9d9d8512c25cd93e8dfa0ed45c6ad5f2b482019b1b579968a9acf0a9f
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
+oid sha256:ecefbb3f17bb76b6655eb0157c98b5287c17fa4b4c72a6b9068b0823ce9fd18d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bc98a8690d286a0c5c6c74f6f325ac33ceb1fd4ad50ba634b85c5c1612f447
+oid sha256:76d2b2a58cb1fef054c26ee40b50f34fb3a71e56ece66a18947891aede843123
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.006246096189881324,
+  "epoch": 0.009369144284821987,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,49 @@
       "eval_samples_per_second": 15.398,
       "eval_steps_per_second": 15.398,
       "step": 100
+    },
+    {
+      "epoch": 0.006870705808869456,
+      "grad_norm": 99.0,
+      "learning_rate": 0.048776412907378844,
+      "loss": 16.2813,
+      "step": 110
+    },
+    {
+      "epoch": 0.007495315427857589,
+      "grad_norm": 15.0,
+      "learning_rate": 0.04851933072501756,
+      "loss": 14.2515,
+      "step": 120
+    },
+    {
+      "epoch": 0.008119925046845722,
+      "grad_norm": 30.625,
+      "learning_rate": 0.048238566570264485,
+      "loss": 11.9391,
+      "step": 130
+    },
+    {
+      "epoch": 0.008744534665833853,
+      "grad_norm": 24.125,
+      "learning_rate": 0.047934403148824085,
+      "loss": 11.4894,
+      "step": 140
+    },
+    {
+      "epoch": 0.009369144284821987,
+      "grad_norm": 20.75,
+      "learning_rate": 0.047607146727478934,
+      "loss": 11.6593,
+      "step": 150
+    },
+    {
+      "epoch": 0.009369144284821987,
+      "eval_loss": 10.226225852966309,
+      "eval_runtime": 55.6759,
+      "eval_samples_per_second": 15.141,
+      "eval_steps_per_second": 15.141,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -116,7 +159,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -130,7 +173,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4084621639680000.0,
+  "total_flos": 6126932459520000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null