Training in progress, step 15500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b87db48356f50aba644c7f62751e63e8a04ec2268f84e4eba37dd50c1a0411
+oid sha256:538d7daf5a013ebf60e116edb876eb64dea7f4748e30f57ec47e2c9572446b86
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a117e1ecba729ee34a78722b6baa410d7ae44754ab32c14568e8bd85298764
+oid sha256:9e768d48c93dac8fb1cb5f2fa432f2e55b47df8d6600926440ac628e20aa6cf2
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb981e2bdbf592329578c66e6b81722ec222bc355b0ddd3bdc9f7689a385e7a
+oid sha256:8dd5917ddffeb704126b23aed843c5f451e0f433388bd43b50327c7ee53765e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0054105d8fb5cdfddd8876e0968830f9a7aa658759cebb2ad97ea276facb582b
+oid sha256:ff2432b3f1647ef3becac2600c0e8902c31d4989fbe6245d5565a62826aeca81
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08243728429079056,
   "best_model_checkpoint": "./fine-tuned/checkpoint-15000",
-  "epoch": 1.2,
+  "epoch": 1.24,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2347,6 +2347,84 @@
       "eval_samples_per_second": 22.719,
       "eval_steps_per_second": 5.68,
       "step": 15000
+    },
+    {
+      "epoch": 1.204,
+      "grad_norm": 0.15492039918899536,
+      "learning_rate": 1.19436e-05,
+      "loss": 0.0535,
+      "step": 15050
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.0744326263666153,
+      "learning_rate": 1.1883600000000001e-05,
+      "loss": 0.0572,
+      "step": 15100
+    },
+    {
+      "epoch": 1.212,
+      "grad_norm": 0.20596753060817719,
+      "learning_rate": 1.1823600000000001e-05,
+      "loss": 0.0539,
+      "step": 15150
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.15914830565452576,
+      "learning_rate": 1.17636e-05,
+      "loss": 0.0583,
+      "step": 15200
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.16685660183429718,
+      "learning_rate": 1.1703600000000001e-05,
+      "loss": 0.0566,
+      "step": 15250
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.11385693401098251,
+      "learning_rate": 1.1643600000000001e-05,
+      "loss": 0.0542,
+      "step": 15300
+    },
+    {
+      "epoch": 1.228,
+      "grad_norm": 0.12850815057754517,
+      "learning_rate": 1.15836e-05,
+      "loss": 0.0622,
+      "step": 15350
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.17093044519424438,
+      "learning_rate": 1.1523600000000001e-05,
+      "loss": 0.0536,
+      "step": 15400
+    },
+    {
+      "epoch": 1.236,
+      "grad_norm": 0.18593502044677734,
+      "learning_rate": 1.1463600000000002e-05,
+      "loss": 0.0541,
+      "step": 15450
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.16509443521499634,
+      "learning_rate": 1.14036e-05,
+      "loss": 0.0501,
+      "step": 15500
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.08269675076007843,
+      "eval_runtime": 88.0811,
+      "eval_samples_per_second": 22.706,
+      "eval_steps_per_second": 5.677,
+      "step": 15500
     }
   ],
   "logging_steps": 50,
@@ -2366,7 +2444,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.65374734336e+16,
+  "total_flos": 3.775538921472e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null