Training in progress, step 42500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:745b8b1d7e5bd21d472de4928ff7acd2ffa83a677380359019a9c4799912b8d9
+oid sha256:6a9ad8913737016dba8650f3d7e7a145a4ce8913d458d7301634297efd00278c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff26510f9fa790ef0a5e5f59b48491824122de83388e6b8dafee62d5541a9a5f
+oid sha256:674d8858e4474544083140dd69e34c045fc6b88c296cb2ac0d991075b6a9ebd1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1538e2c63d940ef0e1b73a9e8d73309e15231b1a12e77d8cac6d2db2463579dc
+oid sha256:07401c37c6a1bb4042ae60703b7c654f256d7be062ccd8d53ae2bf95d64aab34
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89058407f5b943be63f8348b693549eede8380db14dc40de0b317aff021fa0d0
+oid sha256:03af6009394f4a2fb32c0cb40ddd5c5c4f50ce08dbb2d5a4f3d15eba8d0516e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8,
+  "epoch": 2.8333333333333335,
   "eval_steps": 500,
-  "global_step": 42000,
+  "global_step": 42500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2963,6 +2963,41 @@
       "learning_rate": 1.3404444444444445e-06,
       "loss": 0.0504,
       "step": 42000
+    },
+    {
+      "epoch": 2.8066666666666666,
+      "grad_norm": 0.984207272529602,
+      "learning_rate": 1.296e-06,
+      "loss": 0.0487,
+      "step": 42100
+    },
+    {
+      "epoch": 2.8133333333333335,
+      "grad_norm": 0.0887194350361824,
+      "learning_rate": 1.2515555555555556e-06,
+      "loss": 0.0543,
+      "step": 42200
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.17428313195705414,
+      "learning_rate": 1.2071111111111113e-06,
+      "loss": 0.0543,
+      "step": 42300
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 0.05723314359784126,
+      "learning_rate": 1.1626666666666667e-06,
+      "loss": 0.0496,
+      "step": 42400
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.13802002370357513,
+      "learning_rate": 1.1182222222222224e-06,
+      "loss": 0.0549,
+      "step": 42500
     }
   ],
   "logging_steps": 100,
@@ -2982,7 +3017,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0230492561408e+17,
+  "total_flos": 1.035228413952e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null