Training in progress, step 128, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118883fe84d42e93a332df9a89e3a5026832f1eafd98f42f83a5432e0a24d627
+oid sha256:432594db22472e418bc8195f2b34ba5f65ee1039f0c71cf05a9cbf8831e05f5e
 size 1621370224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3bac25bea09d5a7089ba2fac8b6bde72e9d00fc92278449b0bc608c27b3cf1
+oid sha256:a06b6a1026e5526aa739d8f587fb4500092b80502dc294e7c8afd98f41b007e0
 size 3242908299

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f2ff255d68118c4de8327bf505dcaff3af63433e675cbebb46af8c3ce0d04b
+oid sha256:8ae720c221d378ef0f6be085fc497c223afaa3639f3165b626044847d03ec2ea
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5426356589147288,
+  "epoch": 1.9767441860465116,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 128,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,6 +43,13 @@
       "learning_rate": 4.53125e-06,
       "loss": 0.1049,
       "step": 100
+    },
+    {
+      "epoch": 1.8527131782945736,
+      "grad_norm": 1.4672043323516846,
+      "learning_rate": 1.40625e-06,
+      "loss": 0.0934,
+      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -57,12 +64,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 865206943088640.0,
+  "total_flos": 1108682263756800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null