Training in progress, step 100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7851edd1043360267b2db8577a31064ca1621c04e7df4289b379b9f8a9793999
+oid sha256:dc4ff4a862db7f46e931bc03ba272c34c8f1522376a8a2b406743dfb6aa5becd
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a804dd9adf23eb7826763228d6ef8cbd45f3a451d852daf22e2c4f088aba1d
+oid sha256:09f1f0c8166dadba06fe6fc67f6066bed4cdb1ab73ea5aeb075d20803d8d6d3a
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f0fb1c7e888518dcdfd67ad8c4327597ddef100f84eb6544a0f16da3ca1898
+oid sha256:8b4739482302d1b180f4028bb16db49eef68df7df979486c1d696295c50ea91e
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
+oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03bfcb5cd3899a02f7a89e2033f35f63eb1a6773ac4ce6695121020cac9264f0
+oid sha256:01bc98a8690d286a0c5c6c74f6f325ac33ceb1fd4ad50ba634b85c5c1612f447
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.003123048094940662,
+  "epoch": 0.006246096189881324,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,49 @@
       "eval_samples_per_second": 19.503,
       "eval_steps_per_second": 19.503,
       "step": 50
+    },
+    {
+      "epoch": 0.0037476577139287947,
+      "grad_norm": 110.5,
+      "learning_rate": 0.049698382650241506,
+      "loss": 119.4599,
+      "step": 60
+    },
+    {
+      "epoch": 0.004372267332916927,
+      "grad_norm": 876.0,
+      "learning_rate": 0.04956310770317444,
+      "loss": 79.5745,
+      "step": 70
+    },
+    {
+      "epoch": 0.004996876951905059,
+      "grad_norm": 12.1875,
+      "learning_rate": 0.04940309978877575,
+      "loss": 43.8974,
+      "step": 80
+    },
+    {
+      "epoch": 0.005621486570893191,
+      "grad_norm": 144.0,
+      "learning_rate": 0.04921852002145197,
+      "loss": 24.9981,
+      "step": 90
+    },
+    {
+      "epoch": 0.006246096189881324,
+      "grad_norm": 65.0,
+      "learning_rate": 0.04900955425738262,
+      "loss": 22.4848,
+      "step": 100
+    },
+    {
+      "epoch": 0.006246096189881324,
+      "eval_loss": 19.088651657104492,
+      "eval_runtime": 54.7485,
+      "eval_samples_per_second": 15.398,
+      "eval_steps_per_second": 15.398,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -73,7 +116,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -87,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2042310819840000.0,
+  "total_flos": 4084621639680000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null