Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93011cd6be44f102aa1aa5aeb84d12269e0efae6b0ef50d2228b503416b65111
+oid sha256:b4914014d0048ad419fae9de3c869e8a9a3d01941ac99d4fb0d4e64993586925
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d77b1cb0ed498d1a85837eecb2cfff161a459abf45d75920ad0e7990de7147d
+oid sha256:a0d6710d4838767ab1eabb79915f8d054b5869aa459ff20b6ec3b53afb8931b9
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd6d01ae950f4d3fd722c2bf62f25562c692b67847941c0abb1d8dbff1ce11d
+oid sha256:686e4f08928bc0c19b99582b6c5fe9ffd12480ee988aecee97f880477c357d0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941c583f364382ddaf78c0e2c44dbec1776b0a9ac38b7b02ed39492ba5ed849b
+oid sha256:2b0190d5e62eedbb928211e3640963587aa6f015e5105ee6ffcc852c37876753
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.13329531252384186,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-500",
-  "epoch": 0.08781944322472995,
+  "best_metric": 0.12485189735889435,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
+  "epoch": 0.1756388864494599,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,6 +117,116 @@
       "eval_samples_per_second": 25.461,
       "eval_steps_per_second": 3.185,
       "step": 500
+    },
+    {
+      "epoch": 0.09660138754720295,
+      "grad_norm": 16192.8515625,
+      "learning_rate": 2.927542596170736e-05,
+      "loss": 0.1444,
+      "step": 550
+    },
+    {
+      "epoch": 0.10538333186967595,
+      "grad_norm": 20510.47265625,
+      "learning_rate": 2.9209555594589847e-05,
+      "loss": 0.1466,
+      "step": 600
+    },
+    {
+      "epoch": 0.10538333186967595,
+      "eval_loss": 0.1307835429906845,
+      "eval_runtime": 175.06,
+      "eval_samples_per_second": 25.477,
+      "eval_steps_per_second": 3.187,
+      "step": 600
+    },
+    {
+      "epoch": 0.11416527619214895,
+      "grad_norm": 10555.8408203125,
+      "learning_rate": 2.9143685227472337e-05,
+      "loss": 0.1472,
+      "step": 650
+    },
+    {
+      "epoch": 0.12294722051462194,
+      "grad_norm": 12451.990234375,
+      "learning_rate": 2.907781486035482e-05,
+      "loss": 0.1415,
+      "step": 700
+    },
+    {
+      "epoch": 0.12294722051462194,
+      "eval_loss": 0.1288571059703827,
+      "eval_runtime": 175.1799,
+      "eval_samples_per_second": 25.46,
+      "eval_steps_per_second": 3.185,
+      "step": 700
+    },
+    {
+      "epoch": 0.13172916483709493,
+      "grad_norm": 11173.96875,
+      "learning_rate": 2.901194449323731e-05,
+      "loss": 0.1368,
+      "step": 750
+    },
+    {
+      "epoch": 0.14051110915956794,
+      "grad_norm": 47561.75,
+      "learning_rate": 2.8946074126119797e-05,
+      "loss": 0.1399,
+      "step": 800
+    },
+    {
+      "epoch": 0.14051110915956794,
+      "eval_loss": 0.12726937234401703,
+      "eval_runtime": 175.2229,
+      "eval_samples_per_second": 25.453,
+      "eval_steps_per_second": 3.185,
+      "step": 800
+    },
+    {
+      "epoch": 0.14929305348204092,
+      "grad_norm": 11766.6767578125,
+      "learning_rate": 2.8880203759002283e-05,
+      "loss": 0.1433,
+      "step": 850
+    },
+    {
+      "epoch": 0.15807499780451392,
+      "grad_norm": 14977.416015625,
+      "learning_rate": 2.881433339188477e-05,
+      "loss": 0.1371,
+      "step": 900
+    },
+    {
+      "epoch": 0.15807499780451392,
+      "eval_loss": 0.12529444694519043,
+      "eval_runtime": 174.8253,
+      "eval_samples_per_second": 25.511,
+      "eval_steps_per_second": 3.192,
+      "step": 900
+    },
+    {
+      "epoch": 0.1668569421269869,
+      "grad_norm": 11109.173828125,
+      "learning_rate": 2.874846302476726e-05,
+      "loss": 0.1292,
+      "step": 950
+    },
+    {
+      "epoch": 0.1756388864494599,
+      "grad_norm": 9897.7958984375,
+      "learning_rate": 2.8682592657649747e-05,
+      "loss": 0.1351,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1756388864494599,
+      "eval_loss": 0.12485189735889435,
+      "eval_runtime": 174.8115,
+      "eval_samples_per_second": 25.513,
+      "eval_steps_per_second": 3.192,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -136,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null