Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d220ecc16a6dfc89422bca61f2e82fa5409c8e0025b733a0084094bebb3ad38
+oid sha256:5aacaf54054c9481ab96f4c124aec209c4d1863401659f98c84a616c7cf3b550
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732697ac83fc07fe43a3d59c6ed5cfdde9a44eb04f5a28df82f1bae231ebecac
+oid sha256:a8f332eb9f4d28577df53d3028e51e20450cadb931e86cac2055b40c315a56d9
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f0336fd2179ac86a5ce6aaf8830eebae152619763d875677000624b0d5df8f
+oid sha256:bcc8dbed04c9f3746bd0fa583310ef7861dc750445ac3c5d408dc532e0ad467a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:661fa99b8052c174bd0009dc67982291a9f4a6f70e6b8d4ec974bec23de59a1d
+oid sha256:a2b3eacb375d6a673591c6a5df9c962d90dc8b2211d5552b0eeae2d8a3b7ae27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08371368050575256,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-10000",
-  "epoch": 0.8,
+  "best_metric": 0.08319947868585587,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-10500",
+  "epoch": 0.84,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1567,6 +1567,84 @@
       "eval_samples_per_second": 22.712,
       "eval_steps_per_second": 5.678,
       "step": 10000
+    },
+    {
+      "epoch": 0.804,
+      "grad_norm": 0.16905057430267334,
+      "learning_rate": 1.79424e-05,
+      "loss": 0.065,
+      "step": 10050
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.11961635947227478,
+      "learning_rate": 1.7882400000000003e-05,
+      "loss": 0.0677,
+      "step": 10100
+    },
+    {
+      "epoch": 0.812,
+      "grad_norm": 0.13067485392093658,
+      "learning_rate": 1.78224e-05,
+      "loss": 0.0611,
+      "step": 10150
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.12020887434482574,
+      "learning_rate": 1.77624e-05,
+      "loss": 0.0582,
+      "step": 10200
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1354004591703415,
+      "learning_rate": 1.7702400000000002e-05,
+      "loss": 0.0592,
+      "step": 10250
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.22322942316532135,
+      "learning_rate": 1.7642400000000002e-05,
+      "loss": 0.0644,
+      "step": 10300
+    },
+    {
+      "epoch": 0.828,
+      "grad_norm": 0.12816545367240906,
+      "learning_rate": 1.7582400000000003e-05,
+      "loss": 0.065,
+      "step": 10350
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.07579780369997025,
+      "learning_rate": 1.75224e-05,
+      "loss": 0.057,
+      "step": 10400
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 0.10635198652744293,
+      "learning_rate": 1.74624e-05,
+      "loss": 0.062,
+      "step": 10450
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.10341114550828934,
+      "learning_rate": 1.74024e-05,
+      "loss": 0.0593,
+      "step": 10500
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.08319947868585587,
+      "eval_runtime": 88.0121,
+      "eval_samples_per_second": 22.724,
+      "eval_steps_per_second": 5.681,
+      "step": 10500
     }
   ],
   "logging_steps": 50,
@@ -1586,7 +1664,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.43583156224e+16,
+  "total_flos": 2.557623140352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null