Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82551d15f6384cb873b544e144c1f4a47713f4d120acfb3fbb93f105eb65230
+oid sha256:89d970941693f2a588e9760f579c7f92a3993862857386f4ce7a42732003bed9
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2430d0f4d73641065e9bf5dd721f5eb31d0400c5f5950d844482b26db026c2da
+oid sha256:fa728c323613f14720350a34b8de9e9bb0f00feb6895e9763f98b41fc90ba66a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8295ae519bb42d65fe3f9c31072a390aa31ad86276d0cec6598329f84d5b468f
+oid sha256:6f6fa31d853fe83023de7f7f07d4ad55cd60c82617211a8926ae6bb50464d9fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2529f9270ae0263cc98da512a0bbd9cfce3aaadf2f105e2a962446a19cb9d893
+oid sha256:8a8f1b9bc1d96d7439df35e8166ab30771f48f3a8a26970884d1d49063118f39
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0824647843837738,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 1.0,
+  "epoch": 1.04,
   "eval_steps": 500,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1957,6 +1957,84 @@
       "eval_samples_per_second": 22.714,
       "eval_steps_per_second": 5.678,
       "step": 12500
+    },
+    {
+      "epoch": 1.004,
+      "grad_norm": 0.12758083641529083,
+      "learning_rate": 1.4942400000000001e-05,
+      "loss": 0.0553,
+      "step": 12550
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.14093191921710968,
+      "learning_rate": 1.4882400000000002e-05,
+      "loss": 0.0572,
+      "step": 12600
+    },
+    {
+      "epoch": 1.012,
+      "grad_norm": 0.20115911960601807,
+      "learning_rate": 1.48224e-05,
+      "loss": 0.055,
+      "step": 12650
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.2974820137023926,
+      "learning_rate": 1.4762400000000001e-05,
+      "loss": 0.0548,
+      "step": 12700
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.06170056387782097,
+      "learning_rate": 1.47024e-05,
+      "loss": 0.0528,
+      "step": 12750
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.18193961679935455,
+      "learning_rate": 1.46424e-05,
+      "loss": 0.0551,
+      "step": 12800
+    },
+    {
+      "epoch": 1.028,
+      "grad_norm": 0.11086717993021011,
+      "learning_rate": 1.4582400000000001e-05,
+      "loss": 0.0533,
+      "step": 12850
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.1452319473028183,
+      "learning_rate": 1.45224e-05,
+      "loss": 0.0525,
+      "step": 12900
+    },
+    {
+      "epoch": 1.036,
+      "grad_norm": 0.16397640109062195,
+      "learning_rate": 1.44624e-05,
+      "loss": 0.0622,
+      "step": 12950
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.09709367156028748,
+      "learning_rate": 1.4402400000000001e-05,
+      "loss": 0.0559,
+      "step": 13000
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 0.08302706480026245,
+      "eval_runtime": 88.0122,
+      "eval_samples_per_second": 22.724,
+      "eval_steps_per_second": 5.681,
+      "step": 13000
     }
   ],
   "logging_steps": 50,
@@ -1976,7 +2054,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0447894528e+16,
+  "total_flos": 3.166581030912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null