Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111fae1548f3a9e4f827e0a222ad7edb06e8428eef019de781f36b776c406b79
+oid sha256:c97c07b83abbe8d87234d5910a1764e1ee83989dcf8b9b12a5f287e98a942ce0
 size 80339912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10045dcd132c14ffd8adee8b10a6400288c68a416873214d8d5be93e9aa4751
+oid sha256:399c1f89c8e49617c9e528df3179764baaa455be1acd6ae10a8c787e043e7cb1
 size 160724922

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": 300,
   "best_metric": 9.95163631439209,
   "best_model_checkpoint": "./models/v-002/checkpoint-300",
-  "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": 8.245,
       "eval_steps_per_second": 0.519,
       "step": 1900
+    },
+    {
+      "epoch": 61.94565217391305,
+      "grad_norm": 1.4467366933822632,
+      "learning_rate": 8.236784546933718e-07,
+      "loss": 2.9203,
+      "step": 1920
+    },
+    {
+      "epoch": 62.58695652173913,
+      "grad_norm": 1.4114439487457275,
+      "learning_rate": 4.676975846132692e-07,
+      "loss": 2.9122,
+      "step": 1940
+    },
+    {
+      "epoch": 63.22826086956522,
+      "grad_norm": 1.4180433750152588,
+      "learning_rate": 2.1146817970871258e-07,
+      "loss": 2.8226,
+      "step": 1960
+    },
+    {
+      "epoch": 63.880434782608695,
+      "grad_norm": 1.2865217924118042,
+      "learning_rate": 5.550625190150483e-08,
+      "loss": 2.9092,
+      "step": 1980
+    },
+    {
+      "epoch": 64.52173913043478,
+      "grad_norm": 1.3576589822769165,
+      "learning_rate": 1.2588775841204658e-10,
+      "loss": 2.8351,
+      "step": 2000
+    },
+    {
+      "epoch": 64.52173913043478,
+      "eval_accuracy": 0.00042366445774946244,
+      "eval_loss": 10.703904151916504,
+      "eval_runtime": 24.5786,
+      "eval_samples_per_second": 12.287,
+      "eval_steps_per_second": 0.773,
+      "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": 3418254764806656.0,
+  "total_flos": 3598365753291264.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null