Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f7ad03559d709a4e2e50b069ded790243b605bd7f371ff573649b04f3b9ec1
+oid sha256:c9704e41640d7704f052e32113e34a80ebd155dba2fd8f3a818c35af9ef8e5e5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b31881fd08d1c5e92f4d85e7ad4bea7caf87612bcfd05226d0426ef46f64b4
+oid sha256:38547c985ce9b90055e73bc70569507cc2022f06756bda43feaaa7134440ed4a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8e3657fd3e577ff4e755452808dc3c4520d43cd58c493adfa9663f21feb734
+oid sha256:3f2249892101c67b7f09df7f3b33fbce8ad4fc7b712e0895251ba03419a8b657
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc96f5c8ec054c4dc9f1608ed0c88e89518d2f17c416476f4efe7bf3b829bb03
+oid sha256:2dd16cd3f7a9b47079af7541224a232c825207a9e0cc8410dcba6e13de89ef34
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0824647843837738,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 1.08,
+  "epoch": 1.12,
   "eval_steps": 500,
-  "global_step": 13500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2113,6 +2113,84 @@
       "eval_samples_per_second": 22.715,
       "eval_steps_per_second": 5.679,
       "step": 13500
+    },
+    {
+      "epoch": 1.084,
+      "grad_norm": 0.1615404486656189,
+      "learning_rate": 1.3743600000000002e-05,
+      "loss": 0.0572,
+      "step": 13550
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.1500886082649231,
+      "learning_rate": 1.36836e-05,
+      "loss": 0.0557,
+      "step": 13600
+    },
+    {
+      "epoch": 1.092,
+      "grad_norm": 0.08288303017616272,
+      "learning_rate": 1.3623600000000001e-05,
+      "loss": 0.0567,
+      "step": 13650
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.12978018820285797,
+      "learning_rate": 1.3563600000000002e-05,
+      "loss": 0.051,
+      "step": 13700
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.17383359372615814,
+      "learning_rate": 1.35036e-05,
+      "loss": 0.0527,
+      "step": 13750
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.21195685863494873,
+      "learning_rate": 1.3443600000000001e-05,
+      "loss": 0.0526,
+      "step": 13800
+    },
+    {
+      "epoch": 1.108,
+      "grad_norm": 0.15831385552883148,
+      "learning_rate": 1.33836e-05,
+      "loss": 0.0595,
+      "step": 13850
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.23136693239212036,
+      "learning_rate": 1.33236e-05,
+      "loss": 0.0523,
+      "step": 13900
+    },
+    {
+      "epoch": 1.116,
+      "grad_norm": 0.12520194053649902,
+      "learning_rate": 1.3263600000000001e-05,
+      "loss": 0.0603,
+      "step": 13950
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.10329103469848633,
+      "learning_rate": 1.32036e-05,
+      "loss": 0.0494,
+      "step": 14000
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.083070769906044,
+      "eval_runtime": 88.0459,
+      "eval_samples_per_second": 22.715,
+      "eval_steps_per_second": 5.679,
+      "step": 14000
     }
   ],
   "logging_steps": 50,
@@ -2132,7 +2210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.288372609024e+16,
+  "total_flos": 3.410164187136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null