Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28072047700e1de585a07077ebc92b4714eed04f2345d75eb99ced2196fe9fa7
+oid sha256:d44daa9f54039c6a7c112e61fc03e79ec195dfbc876d5e9ced3f4491bafe05b5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c3a16a887489600f444738e291b8186e27ffbeb4f43a529a4469099c5dc85f
+oid sha256:a5c2bc227bc3f6d19424b7e3fb6e1f890007183e4569ce0175d186b2f545cd1d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d505bc797ae06b42ca84d6f450fca5d6d2f612a42f19f5b2b9faeb52b37e39
+oid sha256:0bd1a1233fd369cd2fe83300436739906b8c0f2d7a7cea881535c02b97b11121
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5042add55b1f9bbff03a2f79c52bf9eb682e629b3af75c9a351c18dbe12735bf
+oid sha256:feab8bd3d670dd033dd040441a4a555712fd3da457861c798e89356180e76612
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.10637149214744568,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-7000",
-  "epoch": 1.2294722051462195,
+  "best_metric": 0.1062735840678215,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-7500",
+  "epoch": 1.3172916483709494,
   "eval_steps": 100,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1547,6 +1547,116 @@
       "eval_samples_per_second": 25.293,
       "eval_steps_per_second": 3.165,
       "step": 7000
+    },
+    {
+      "epoch": 1.2382541494686923,
+      "grad_norm": 32394.365234375,
+      "learning_rate": 2.0712278236430705e-05,
+      "loss": 0.1082,
+      "step": 7050
+    },
+    {
+      "epoch": 1.2470360937911653,
+      "grad_norm": 13041.302734375,
+      "learning_rate": 2.0646407869313192e-05,
+      "loss": 0.1118,
+      "step": 7100
+    },
+    {
+      "epoch": 1.2470360937911653,
+      "eval_loss": 0.10657413303852081,
+      "eval_runtime": 176.3827,
+      "eval_samples_per_second": 25.286,
+      "eval_steps_per_second": 3.164,
+      "step": 7100
+    },
+    {
+      "epoch": 1.2558180381136383,
+      "grad_norm": 9132.3310546875,
+      "learning_rate": 2.0580537502195682e-05,
+      "loss": 0.103,
+      "step": 7150
+    },
+    {
+      "epoch": 1.2645999824361114,
+      "grad_norm": 18166.306640625,
+      "learning_rate": 2.0514667135078165e-05,
+      "loss": 0.1108,
+      "step": 7200
+    },
+    {
+      "epoch": 1.2645999824361114,
+      "eval_loss": 0.10623560100793839,
+      "eval_runtime": 176.2458,
+      "eval_samples_per_second": 25.306,
+      "eval_steps_per_second": 3.166,
+      "step": 7200
+    },
+    {
+      "epoch": 1.2733819267585844,
+      "grad_norm": 12996.111328125,
+      "learning_rate": 2.0448796767960652e-05,
+      "loss": 0.1019,
+      "step": 7250
+    },
+    {
+      "epoch": 1.2821638710810572,
+      "grad_norm": 9010.8212890625,
+      "learning_rate": 2.0382926400843142e-05,
+      "loss": 0.1074,
+      "step": 7300
+    },
+    {
+      "epoch": 1.2821638710810572,
+      "eval_loss": 0.10622620582580566,
+      "eval_runtime": 176.3743,
+      "eval_samples_per_second": 25.287,
+      "eval_steps_per_second": 3.164,
+      "step": 7300
+    },
+    {
+      "epoch": 1.2909458154035303,
+      "grad_norm": 14462.72265625,
+      "learning_rate": 2.031705603372563e-05,
+      "loss": 0.1104,
+      "step": 7350
+    },
+    {
+      "epoch": 1.2997277597260033,
+      "grad_norm": 9121.498046875,
+      "learning_rate": 2.0251185666608115e-05,
+      "loss": 0.1141,
+      "step": 7400
+    },
+    {
+      "epoch": 1.2997277597260033,
+      "eval_loss": 0.10618162155151367,
+      "eval_runtime": 176.2451,
+      "eval_samples_per_second": 25.306,
+      "eval_steps_per_second": 3.166,
+      "step": 7400
+    },
+    {
+      "epoch": 1.3085097040484763,
+      "grad_norm": 13231.1484375,
+      "learning_rate": 2.0185315299490602e-05,
+      "loss": 0.1106,
+      "step": 7450
+    },
+    {
+      "epoch": 1.3172916483709494,
+      "grad_norm": 8816.541015625,
+      "learning_rate": 2.0119444932373092e-05,
+      "loss": 0.1065,
+      "step": 7500
+    },
+    {
+      "epoch": 1.3172916483709494,
+      "eval_loss": 0.1062735840678215,
+      "eval_runtime": 176.3513,
+      "eval_samples_per_second": 25.29,
+      "eval_steps_per_second": 3.164,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1566,7 +1676,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.409951051874304e+16,
+  "total_flos": 3.653534208098304e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null