Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d30cd2d3ba0a118bc44f9ffe1d61ae733ab7391c3505d0fc6142257dd9d870
+oid sha256:67dbb13c1700a23a3cd944e85aebc73b962d3f76d94eb4a52c140ccaf7361dc6
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bd918839235450e7016529117061462575bd438ab59c7e4f497daf14c0a307
+oid sha256:a8165032ea424772ac69fdaacaaaa571681c1d2179d8967aaf7946a8d90faaab
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7951b102fa0035de952f0290adc9e70cb93d5096767428189697cc1180764452
+oid sha256:010a2984d2c14ea7f828d2ed740e96d06dd0386afc32f424d17a7b98c9383d42
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2bebcb74fda4a7dc9be8feacd74ba4435f508244bde8e9024e695137478735
+oid sha256:eb5fb5e686bee457697966152ad172eba58d6c49cee8cb273e14d35ebb08713f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.1056413650512695,
   "best_model_checkpoint": "./opt_trained1/checkpoint-201",
-  "epoch": 1.9956656346749226,
+  "epoch": 2.9956656346749226,
   "eval_steps": 500,
-  "global_step": 402,
+  "global_step": 603,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 13.824,
       "eval_steps_per_second": 1.734,
       "step": 402
+    },
+    {
+      "epoch": 2.485448916408669,
+      "grad_norm": 283244.78125,
+      "learning_rate": 8.756218905472637e-05,
+      "loss": 3.2084,
+      "step": 500
+    },
+    {
+      "epoch": 2.9956656346749226,
+      "eval_loss": 8.332228660583496,
+      "eval_runtime": 155.8264,
+      "eval_samples_per_second": 13.817,
+      "eval_steps_per_second": 1.733,
+      "step": 603
     }
   ],
   "logging_steps": 500,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7234811969929216e+16,
+  "total_flos": 4.085221795489382e+16,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null