Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765bfcf6d0a8ff21930d4e9fe4b2b599be26666bec8eea3a16e4c84ba3ffc95b
+oid sha256:c1dd5dadc46fc8d5d568e46e43f3b6ea2ebfc051344639f8f119a25601e1d67e
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06d0818ffb6f94acbca1738cf11629fec58d3d8b41653fa15dfcf476cc8f4c5
+oid sha256:d8f9cd5b4816a26073d22aa15eaeca1dc70350f27ca90aba1308836d4e9e1886
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08945245467a1f4ba1b221d623a851c3f1d1e4decc22c63851542baa5c3c1005
+oid sha256:a6037549dfd291b40e6013a8226b5232149d6bae666b5596a4d76146c60fb310
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a65eba1ec74814d8e1a895511acf1700c8655b3f38d31b42149c09c53ea1cd4
+oid sha256:f560d449ba2ae2773abf472ac9c8668f9b0647f45029741e5b3eaa3eedd0b37e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4066200256347656,
   "best_model_checkpoint": "mikhail_panzo/fil_b32_le4_s8000/checkpoint-5500",
-  "epoch": 120.87912087912088,
+  "epoch": 131.86813186813185,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 13.239,
       "eval_steps_per_second": 1.727,
       "step": 5500
+    },
+    {
+      "epoch": 121.97802197802197,
+      "grad_norm": 1.4458872079849243,
+      "learning_rate": 4.0883333333333335e-05,
+      "loss": 0.3685,
+      "step": 5550
+    },
+    {
+      "epoch": 123.07692307692308,
+      "grad_norm": 1.9380217790603638,
+      "learning_rate": 4.0050000000000004e-05,
+      "loss": 0.3689,
+      "step": 5600
+    },
+    {
+      "epoch": 124.17582417582418,
+      "grad_norm": 1.1235325336456299,
+      "learning_rate": 3.921666666666667e-05,
+      "loss": 0.3735,
+      "step": 5650
+    },
+    {
+      "epoch": 125.27472527472527,
+      "grad_norm": 1.0528467893600464,
+      "learning_rate": 3.8383333333333336e-05,
+      "loss": 0.3645,
+      "step": 5700
+    },
+    {
+      "epoch": 126.37362637362638,
+      "grad_norm": 0.8706468939781189,
+      "learning_rate": 3.7550000000000005e-05,
+      "loss": 0.3651,
+      "step": 5750
+    },
+    {
+      "epoch": 127.47252747252747,
+      "grad_norm": 2.1038143634796143,
+      "learning_rate": 3.671666666666667e-05,
+      "loss": 0.3655,
+      "step": 5800
+    },
+    {
+      "epoch": 128.57142857142858,
+      "grad_norm": 1.101017951965332,
+      "learning_rate": 3.5883333333333336e-05,
+      "loss": 0.3652,
+      "step": 5850
+    },
+    {
+      "epoch": 129.67032967032966,
+      "grad_norm": 2.1845877170562744,
+      "learning_rate": 3.505e-05,
+      "loss": 0.3637,
+      "step": 5900
+    },
+    {
+      "epoch": 130.76923076923077,
+      "grad_norm": 1.1006217002868652,
+      "learning_rate": 3.421666666666667e-05,
+      "loss": 0.362,
+      "step": 5950
+    },
+    {
+      "epoch": 131.86813186813185,
+      "grad_norm": 1.1332905292510986,
+      "learning_rate": 3.3383333333333336e-05,
+      "loss": 0.3665,
+      "step": 6000
+    },
+    {
+      "epoch": 131.86813186813185,
+      "eval_loss": 0.40923577547073364,
+      "eval_runtime": 11.9318,
+      "eval_samples_per_second": 13.493,
+      "eval_steps_per_second": 1.76,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2617494075013056e+16,
+  "total_flos": 3.557860355581488e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null