Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8abfe1c45075397ba78eddd89c5994752695b01235a42386bb761a82867fffd
+oid sha256:b676eb1cce389fad67f783ed88d91dc052376e7052045e7cb24d89bec7882264
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1dcd687a174176e1e1353bdf8c3d4d81b11a8c9d8db70bc8b35711ba8985b90
+oid sha256:deaef2792c3b5285ed991700879739e46c21e969fcdf385e8825f314570c1445
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3c2ed273b6fd046d73eece671d41adbebd5d981151c021863b9f0838a40432
+oid sha256:1e123b7d674edffd979d1e86b4d3aff1fd5f75a80012e2a39bac505db90d8321
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010114107883817428,
+  "epoch": 0.012966804979253113,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 33.4698,
       "step": 35
+    },
+    {
+      "epoch": 0.01037344398340249,
+      "grad_norm": 7668.44775390625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 31.6229,
+      "step": 40
+    },
+    {
+      "epoch": 0.01037344398340249,
+      "eval_loss": 8.130403518676758,
+      "eval_runtime": 11.8434,
+      "eval_samples_per_second": 137.123,
+      "eval_steps_per_second": 68.562,
+      "step": 40
+    },
+    {
+      "epoch": 0.011670124481327801,
+      "grad_norm": 10333.982421875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 33.1746,
+      "step": 45
+    },
+    {
+      "epoch": 0.012966804979253113,
+      "grad_norm": 6658.6396484375,
+      "learning_rate": 0.0,
+      "loss": 34.0631,
+      "step": 50
+    },
+    {
+      "epoch": 0.012966804979253113,
+      "eval_loss": 8.104995727539062,
+      "eval_runtime": 11.4936,
+      "eval_samples_per_second": 141.297,
+      "eval_steps_per_second": 70.648,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7833428951040.0,
+  "total_flos": 10112244645888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null