Training in progress, step 5692, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa3dfa629d6f0a4b00e9aa0db2fda3e9ab1e4c509f72b23ef5457288b2e474f
+oid sha256:3282a74e588d167af885979217f2163838ce9140b961d4759ca970b8f45a34f8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9c7ab2e3359d64280354b30eccac6666a4328bc54eac0eee212a29f2aaf43c
+oid sha256:d991a87c3c47037577ad22c7ff6d19f18ff612aa04b6016ab49561b700922f83
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a194bef12ceeecc6ad10e9d032a837c1a3c1db13b2c2253686b43518ae42503
+oid sha256:6a37fbc263c505f02f6ce9dcccc6ed9c167c85ba9bd4249a320a5f924d43f35b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66a57bd394806719fb22948b621f468b035d0a2c7c49f5f8b90d526b96103c4
+oid sha256:d4ca5c4e853eca5507dffbf1162373b8e51b2a8cdc79c4e01dce5ddf18b3fd7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.20129592716693878,
   "best_model_checkpoint": "./fine-tuned/checkpoint-5500",
-  "epoch": 3.8637161924833157,
+  "epoch": 3.9985950122936424,
   "eval_steps": 100,
-  "global_step": 5500,
+  "global_step": 5692,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1217,6 +1217,35 @@
       "eval_samples_per_second": 66.382,
       "eval_steps_per_second": 2.084,
       "step": 5500
+    },
+    {
+      "epoch": 3.898840885142255,
+      "grad_norm": 22639.22265625,
+      "learning_rate": 7.484188334504568e-07,
+      "loss": 0.1898,
+      "step": 5550
+    },
+    {
+      "epoch": 3.933965577801194,
+      "grad_norm": 108627.9453125,
+      "learning_rate": 4.848910751932538e-07,
+      "loss": 0.1887,
+      "step": 5600
+    },
+    {
+      "epoch": 3.933965577801194,
+      "eval_loss": 0.2013484090566635,
+      "eval_runtime": 67.1981,
+      "eval_samples_per_second": 66.371,
+      "eval_steps_per_second": 2.083,
+      "step": 5600
+    },
+    {
+      "epoch": 3.9690902704601334,
+      "grad_norm": 28155.427734375,
+      "learning_rate": 2.213633169360506e-07,
+      "loss": 0.1955,
+      "step": 5650
     }
   ],
   "logging_steps": 50,
@@ -1231,12 +1260,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.35814435930112e+16,
+  "total_flos": 5.545216223281152e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null