Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb5510d1b55f44ce0aad6fca441bbd65fd2fcbf55153ec23422d5bfa442e83c
+oid sha256:463e50976fdd4523d72dfa1f9dde00e7d2fb94044b71ff95fa42ebac380383f9
 size 136062744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c47860f969d19f1732995ffddb49a5f9ba7e408d1dd376ecac4a2b77aeec61f
+oid sha256:0622f360da035ed6f191ceef1a70160b2b4f027c1bb245098847e56aae470e88
 size 138234066

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d51e4a7056c3558a387ed54a4d13c51368f1e567102a0ee859969fb5f31cd3
+oid sha256:da2a7e5837e8166f34d69c47cbcb9c5f754b8d9aaee67ec69e6f2fe466d72356
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1204ca9be37de89665f7f1742f206de4543c6c56db448f2a4968fb174cdf1393
+oid sha256:bd3708ae31f1069fc45ac5848423f03f6df0cd0e16b6138df98e3ba73d336476
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0160b3598707f8907336269c674f5ce56b2bbdea80b3e53648f4959f2a4937ca
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 42.30769230769231,
+  "epoch": 46.15384615384615,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -488,6 +488,49 @@
       "eval_samples_per_second": 265.392,
       "eval_steps_per_second": 4.243,
       "step": 550
+    },
+    {
+      "epoch": 43.07692307692308,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.420361737256438e-06,
+      "loss": 0.6671,
+      "step": 560
+    },
+    {
+      "epoch": 43.84615384615385,
+      "grad_norm": 0.62890625,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.6683,
+      "step": 570
+    },
+    {
+      "epoch": 44.61538461538461,
+      "grad_norm": 0.59375,
+      "learning_rate": 6.069322682050516e-07,
+      "loss": 0.6714,
+      "step": 580
+    },
+    {
+      "epoch": 45.38461538461539,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.518483566683826e-07,
+      "loss": 0.6695,
+      "step": 590
+    },
+    {
+      "epoch": 46.15384615384615,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.0,
+      "loss": 0.6667,
+      "step": 600
+    },
+    {
+      "epoch": 46.15384615384615,
+      "eval_loss": 4.010259628295898,
+      "eval_runtime": 5.6787,
+      "eval_samples_per_second": 264.32,
+      "eval_steps_per_second": 4.226,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -502,12 +545,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.87955788382208e+16,
+  "total_flos": 2.05042678235136e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null