Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538d7daf5a013ebf60e116edb876eb64dea7f4748e30f57ec47e2c9572446b86
+oid sha256:1d7224364f596ebfca3a99c1d3b9d449fb04ce1b01252f00b468ebb7f2583738
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e768d48c93dac8fb1cb5f2fa432f2e55b47df8d6600926440ac628e20aa6cf2
+oid sha256:c146dfaf517426e21001d58ecb591e013237c1f0457fc2b2e18c8128376dd232
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd5917ddffeb704126b23aed843c5f451e0f433388bd43b50327c7ee53765e0
+oid sha256:0e2dd927672719d15b56be948c4d341bf0d4717fdddd441106e1853c80a9c881
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2432b3f1647ef3becac2600c0e8902c31d4989fbe6245d5565a62826aeca81
+oid sha256:fc65b1cc8bef515a746903c5c0ceccfd01df11517dd7fe9004c63360d9c9a98b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08243728429079056,
   "best_model_checkpoint": "./fine-tuned/checkpoint-15000",
-  "epoch": 1.24,
+  "epoch": 1.28,
   "eval_steps": 500,
-  "global_step": 15500,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2425,6 +2425,84 @@
       "eval_samples_per_second": 22.706,
       "eval_steps_per_second": 5.677,
       "step": 15500
+    },
+    {
+      "epoch": 1.244,
+      "grad_norm": 0.15668867528438568,
+      "learning_rate": 1.1343600000000001e-05,
+      "loss": 0.0534,
+      "step": 15550
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.08703252673149109,
+      "learning_rate": 1.12836e-05,
+      "loss": 0.0534,
+      "step": 15600
+    },
+    {
+      "epoch": 1.252,
+      "grad_norm": 0.1255914270877838,
+      "learning_rate": 1.12248e-05,
+      "loss": 0.0514,
+      "step": 15650
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.11858811974525452,
+      "learning_rate": 1.11648e-05,
+      "loss": 0.0527,
+      "step": 15700
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.13111431896686554,
+      "learning_rate": 1.1104799999999999e-05,
+      "loss": 0.0494,
+      "step": 15750
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.17452576756477356,
+      "learning_rate": 1.10448e-05,
+      "loss": 0.0562,
+      "step": 15800
+    },
+    {
+      "epoch": 1.268,
+      "grad_norm": 0.13699005544185638,
+      "learning_rate": 1.09848e-05,
+      "loss": 0.051,
+      "step": 15850
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.18750061094760895,
+      "learning_rate": 1.0924799999999999e-05,
+      "loss": 0.0545,
+      "step": 15900
+    },
+    {
+      "epoch": 1.276,
+      "grad_norm": 0.1259056031703949,
+      "learning_rate": 1.08648e-05,
+      "loss": 0.0529,
+      "step": 15950
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.10538329184055328,
+      "learning_rate": 1.08048e-05,
+      "loss": 0.058,
+      "step": 16000
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.08262528479099274,
+      "eval_runtime": 88.074,
+      "eval_samples_per_second": 22.708,
+      "eval_steps_per_second": 5.677,
+      "step": 16000
     }
   ],
   "logging_steps": 50,
@@ -2444,7 +2522,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.775538921472e+16,
+  "total_flos": 3.897330499584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null