Training in progress, step 950, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a213889093690708333a72ba85b3e173a26f185c33fba33332e53260dbd1c4aa
+oid sha256:4725f7683f2b8dc2c37be3613593f25b041ac5cfee2a86d851142562e03f31e2
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972947c98f4763776af4efd2f002616917f749771c80dff97f83bfb67f4acd2d
+oid sha256:fe054c5b7dbc4504491e8399e4c3dd2f601a8021e18628ca1a900249c2072e44
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e127ed7b7fc1b3994f8c17585153440be7f03c26e5b46dbf6c360aa0ff0978e4
+oid sha256:4483c56b3458c6f88b40364283839fd954d028d7abdcc22bb698f9239fe76b79
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82be7d57b17f6620866913ecd4ff8b7c828f1f4bbbb44f8426b657efc6ab9fa7
+oid sha256:645b71843375baf4cc10bc75a2f0f04e91b8e3f8e8929f518a87022898b3bc20
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9eac997032339e8d5b43afb42a0ae765d18d35f79086924503e8ce32f56fdeb
+oid sha256:a288ddd8ddfd7759ce5e03ca2b9f4240d1938c54de141af3734f632c4e8a713b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.056214865708931916,
+  "epoch": 0.05933791380387258,
   "eval_steps": 50,
-  "global_step": 900,
+  "global_step": 950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -790,6 +790,49 @@
       "eval_samples_per_second": 15.627,
       "eval_steps_per_second": 15.627,
       "step": 900
+    },
+    {
+      "epoch": 0.05683947532792005,
+      "grad_norm": 63.5,
+      "learning_rate": 0.0010351471287475406,
+      "loss": 7.814,
+      "step": 910
+    },
+    {
+      "epoch": 0.05746408494690818,
+      "grad_norm": 1088.0,
+      "learning_rate": 0.0008213286324510738,
+      "loss": 7.1516,
+      "step": 920
+    },
+    {
+      "epoch": 0.05808869456589631,
+      "grad_norm": 268.0,
+      "learning_rate": 0.000631856008683518,
+      "loss": 7.2965,
+      "step": 930
+    },
+    {
+      "epoch": 0.05871330418488445,
+      "grad_norm": 600.0,
+      "learning_rate": 0.00046692004031609894,
+      "loss": 7.5007,
+      "step": 940
+    },
+    {
+      "epoch": 0.05933791380387258,
+      "grad_norm": 148.0,
+      "learning_rate": 0.0003266868038879434,
+      "loss": 7.4526,
+      "step": 950
+    },
+    {
+      "epoch": 0.05933791380387258,
+      "eval_loss": 7.6293864250183105,
+      "eval_runtime": 52.7226,
+      "eval_samples_per_second": 15.989,
+      "eval_steps_per_second": 15.989,
+      "step": 950
     }
   ],
   "logging_steps": 10,
@@ -804,7 +847,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 18
+        "early_stopping_patience_counter": 19
       }
     },
     "TrainerControl": {
@@ -818,7 +861,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.676159475712e+16,
+  "total_flos": 3.880390557696e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null