Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b066dd76450f1fc2cd5dd08d20ae972b8a94050621292c31d8235f96e7108a
+oid sha256:fb86b7f70b45053cb6d55ae4376642fa03d54495b5c27e78b0cd2d46a00b5c0b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8240f13191a1e88e705958073d032c3ea3f1e76fd691d5ec8e01e44a4b1264
+oid sha256:d232a9a6c756331696e700546387d842e2067cae42866a06dd49ad2965fbaa1e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21b33c421be30ae2ef87f38ded5d07cf75a2ddfe995129adfae900c14c14b42
+oid sha256:5b1952f58fa52e592468a775e85ac7e72d5b2b6d4cdb2766a2b20ab5e3f11899
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f138ad5145d2f28383f769cd6a0c1fe56a4d753047d159ec5a6175b52316e4c
+oid sha256:e999a568b2d0f01998dabb86d34bac49ae5618451719e3426ca61159d87ee5c4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3375319242477417,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-500",
-  "epoch": 0.8312551953449709,
+  "best_metric": 0.3063213527202606,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
+  "epoch": 1.6625103906899419,
   "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": 12.924,
       "eval_steps_per_second": 1.622,
       "step": 500
+    },
+    {
+      "epoch": 0.914380714879468,
+      "grad_norm": 60626.75,
+      "learning_rate": 3.856073211314476e-05,
+      "loss": 0.405,
+      "step": 550
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 51910.04296875,
+      "learning_rate": 3.752079866888519e-05,
+      "loss": 0.4186,
+      "step": 600
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "eval_loss": 0.3285529315471649,
+      "eval_runtime": 38.3187,
+      "eval_samples_per_second": 12.892,
+      "eval_steps_per_second": 1.618,
+      "step": 600
+    },
+    {
+      "epoch": 1.0806317539484622,
+      "grad_norm": 48182.8046875,
+      "learning_rate": 3.6480865224625625e-05,
+      "loss": 0.3925,
+      "step": 650
+    },
+    {
+      "epoch": 1.1637572734829593,
+      "grad_norm": 51930.34765625,
+      "learning_rate": 3.544093178036606e-05,
+      "loss": 0.3705,
+      "step": 700
+    },
+    {
+      "epoch": 1.1637572734829593,
+      "eval_loss": 0.3227428197860718,
+      "eval_runtime": 38.1185,
+      "eval_samples_per_second": 12.96,
+      "eval_steps_per_second": 1.627,
+      "step": 700
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 60283.91015625,
+      "learning_rate": 3.4400998336106495e-05,
+      "loss": 0.3823,
+      "step": 750
+    },
+    {
+      "epoch": 1.3300083125519535,
+      "grad_norm": 55843.62109375,
+      "learning_rate": 3.336106489184692e-05,
+      "loss": 0.3763,
+      "step": 800
+    },
+    {
+      "epoch": 1.3300083125519535,
+      "eval_loss": 0.3174193501472473,
+      "eval_runtime": 38.4517,
+      "eval_samples_per_second": 12.847,
+      "eval_steps_per_second": 1.612,
+      "step": 800
+    },
+    {
+      "epoch": 1.4131338320864506,
+      "grad_norm": 40623.88671875,
+      "learning_rate": 3.232113144758736e-05,
+      "loss": 0.3509,
+      "step": 850
+    },
+    {
+      "epoch": 1.4962593516209477,
+      "grad_norm": 57212.0546875,
+      "learning_rate": 3.128119800332779e-05,
+      "loss": 0.3624,
+      "step": 900
+    },
+    {
+      "epoch": 1.4962593516209477,
+      "eval_loss": 0.31218209862709045,
+      "eval_runtime": 38.1558,
+      "eval_samples_per_second": 12.947,
+      "eval_steps_per_second": 1.625,
+      "step": 900
+    },
+    {
+      "epoch": 1.5793848711554448,
+      "grad_norm": 49043.25390625,
+      "learning_rate": 3.0241264559068223e-05,
+      "loss": 0.3656,
+      "step": 950
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 50702.92578125,
+      "learning_rate": 2.9201331114808654e-05,
+      "loss": 0.3741,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "eval_loss": 0.3063213527202606,
+      "eval_runtime": 38.2912,
+      "eval_samples_per_second": 12.901,
+      "eval_steps_per_second": 1.619,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -136,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null