Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3281ea58f21e8e23189595bfa79850858fbba3783269108bb5bca8b74fb39a5
+oid sha256:6b72c0bf22d23a4eb289f371789a956c102b66a845756a44dfb94f6b3dd5e699
 size 86625328

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554ea62f74181baa086e6cb6b5a596623c8aaf0559d81263e36e2fe654a0eeb7
+oid sha256:bd2e8d7109465f06b6ae243956440e37dca0f5e026734b19e349c8f88a2456f9
 size 173285114

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ac6cc9f96cb23f38dad14b3c8b94857940a2c54443bb178825363cab7260c0
+oid sha256:2aecb175b401aad5342b976c594fc9d9720fb1d1217dbf6aec48e9deb3a15dd1
 size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2375bb704062abe009d16c81c5208b4a77486ea2b7e1b6be5a4f624a4401587f
+oid sha256:e301ebd8064bb9799d23981baab716db6ee7302f5ba2efc70a2dd3be85fbcb46
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 800,
   "best_metric": 9.927443504333496,
   "best_model_checkpoint": "./models/v-004/checkpoint-800",
-  "epoch": 61.29347826086956,
+  "epoch": 64.52173913043478,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -844,6 +844,50 @@
       "eval_samples_per_second": 7.067,
       "eval_steps_per_second": 0.445,
       "step": 1900
+    },
+    {
+      "epoch": 61.94565217391305,
+      "grad_norm": 0.9399953484535217,
+      "learning_rate": 8.236784546933718e-07,
+      "loss": 2.7602,
+      "step": 1920
+    },
+    {
+      "epoch": 62.58695652173913,
+      "grad_norm": 0.9184156656265259,
+      "learning_rate": 4.676975846132692e-07,
+      "loss": 2.7586,
+      "step": 1940
+    },
+    {
+      "epoch": 63.22826086956522,
+      "grad_norm": 0.9342102408409119,
+      "learning_rate": 2.1146817970871258e-07,
+      "loss": 2.6681,
+      "step": 1960
+    },
+    {
+      "epoch": 63.880434782608695,
+      "grad_norm": 0.8547150492668152,
+      "learning_rate": 5.550625190150483e-08,
+      "loss": 2.7384,
+      "step": 1980
+    },
+    {
+      "epoch": 64.52173913043478,
+      "grad_norm": 0.9187237024307251,
+      "learning_rate": 1.2588775841204658e-10,
+      "loss": 2.6918,
+      "step": 2000
+    },
+    {
+      "epoch": 64.52173913043478,
+      "eval_accuracy": 0.0003037594225373504,
+      "eval_loss": 10.291138648986816,
+      "eval_runtime": 106.7866,
+      "eval_samples_per_second": 2.828,
+      "eval_steps_per_second": 0.178,
+      "step": 2000
     }
   ],
   "logging_steps": 20,
@@ -858,12 +902,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3851454299490816.0,
+  "total_flos": 4054390970018304.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null