Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb7fdd07abfa119cf7164e53299c607359a9af6799573cd9441c500a5e24222
+oid sha256:a386dbf8561c23ab581d453dcd91a538b003106a42f2c4c69aa89905c576ec94
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8434daa3277e8b219eb59a6668bc14f8e7e4908bd17a2304d8b94d800e65d92
+oid sha256:7cb642c71b31f5e976e9421191ae004cf5d66ac5cbda04966dfe08b3425e655f
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bb9aa3709cd1c036484251854b8be7d825e637d956e7203821b032aa2540e3
+oid sha256:3d3ed9e0dc19a3bb7b5e8c42e476b42194e2ef37d159e54556a02e2773c9c2ab
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541d8b16c337fd96e05a077a2be76d2de8216d931de0afb127b2cab79028732a
+oid sha256:0267fbad859e57b7ff33d6dbd4fbd9fdf3cbf25f82f07754a3b6e19cff3ef2f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 50,
-  "global_step": 387,
+  "global_step": 516,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,51 @@
       "eval_samples_per_second": 37.402,
       "eval_steps_per_second": 18.701,
       "step": 350
+    },
+    {
+      "epoch": 3.101512933138116,
+      "grad_norm": 0.6013683676719666,
+      "learning_rate": 6.875e-05,
+      "loss": 1.2507,
+      "step": 400
+    },
+    {
+      "epoch": 3.101512933138116,
+      "eval_loss": 1.3298077583312988,
+      "eval_runtime": 11.5601,
+      "eval_samples_per_second": 37.37,
+      "eval_steps_per_second": 18.685,
+      "step": 400
+    },
+    {
+      "epoch": 3.49194729136164,
+      "grad_norm": 0.6187678575515747,
+      "learning_rate": 6.484375e-05,
+      "loss": 1.2463,
+      "step": 450
+    },
+    {
+      "epoch": 3.49194729136164,
+      "eval_loss": 1.2986701726913452,
+      "eval_runtime": 11.5395,
+      "eval_samples_per_second": 37.437,
+      "eval_steps_per_second": 18.718,
+      "step": 450
+    },
+    {
+      "epoch": 3.8823816495851635,
+      "grad_norm": 0.5973629951477051,
+      "learning_rate": 6.0937500000000004e-05,
+      "loss": 1.2315,
+      "step": 500
+    },
+    {
+      "epoch": 3.8823816495851635,
+      "eval_loss": 1.2973381280899048,
+      "eval_runtime": 11.5491,
+      "eval_samples_per_second": 37.405,
+      "eval_steps_per_second": 18.703,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -131,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0698953774543667e+17,
+  "total_flos": 1.426527168149586e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null