Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d826c309b9f9492a58d67f6f2eecf7cdd6615d329adca02ac882e7b2d1de12cb
+oid sha256:164eb6a81614e9f1939013796bd9b48e2712186901dcd74df1d6b04dce844484
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a553addc7ddb7e0af58a94d7cce4e00b2edf20465e6287f926268d68186099
+oid sha256:e1b12fd71694fa1ec35a8b9d6e65e079baa75b27e5b9f063a99bdafa82fe1e09
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a7290491808e872bdfba856354703f0501eed54b9da7aaa39843c9c248c6159
+oid sha256:66d55cead2e68dd96646c1b6f8fd0e4361ef538e5be0ae590c27b3898e8c95df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c790c63fb7345bfd79d855efc8355667eb23eb3bcba2a26737d1f0ffb0ba07b
+oid sha256:53ae3cfedd2dd31595a079dd5baf168ac1b0849191aed860395ad88084b14144
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0869474709033966,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-3500",
-  "epoch": 0.28,
+  "best_metric": 0.0867869183421135,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-4000",
+  "epoch": 0.32,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,84 @@
       "eval_samples_per_second": 22.813,
       "eval_steps_per_second": 5.703,
       "step": 3500
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.13956592977046967,
+      "learning_rate": 2.57424e-05,
+      "loss": 0.0749,
+      "step": 3550
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.2318839579820633,
+      "learning_rate": 2.56824e-05,
+      "loss": 0.0658,
+      "step": 3600
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.10267651081085205,
+      "learning_rate": 2.56224e-05,
+      "loss": 0.0651,
+      "step": 3650
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.13903647661209106,
+      "learning_rate": 2.5562399999999998e-05,
+      "loss": 0.0684,
+      "step": 3700
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.07369179278612137,
+      "learning_rate": 2.5502399999999998e-05,
+      "loss": 0.0643,
+      "step": 3750
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.18283645808696747,
+      "learning_rate": 2.54424e-05,
+      "loss": 0.0745,
+      "step": 3800
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.1031743511557579,
+      "learning_rate": 2.5382400000000003e-05,
+      "loss": 0.0678,
+      "step": 3850
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.2246129959821701,
+      "learning_rate": 2.5322400000000003e-05,
+      "loss": 0.0701,
+      "step": 3900
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.1434032917022705,
+      "learning_rate": 2.52624e-05,
+      "loss": 0.071,
+      "step": 3950
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.11730857193470001,
+      "learning_rate": 2.52024e-05,
+      "loss": 0.0696,
+      "step": 4000
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.0867869183421135,
+      "eval_runtime": 87.7801,
+      "eval_samples_per_second": 22.784,
+      "eval_steps_per_second": 5.696,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -572,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8525410467840000.0,
+  "total_flos": 9743326248960000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null