Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9b11f97cd25633ecfc3b36a7374feeb30950d3f29789a0283e672c7dc24e53
+oid sha256:f07e335765ad98bc3016202337473cdf825ee71679b99c6ecd6cfad3288e1d66
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52c93beebd18ce78764aa5240ff0c9b7d0bc73844f7189816ff8647028599d4
+oid sha256:c337c83104bc1d2466bd8ccf29f7361833d292cebb31f379483ff2f1bf0d5a9b
 size 167987322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fef718c3dca7761bb2f89ed5a815a6dc1b58ec2203c7e914a62a57cb6ea24f1
+oid sha256:45c8827f349044224c7f432996e313bccb81b889418433d17cdff84bd2044472
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03040668947168377,
+  "epoch": 0.04561003420752566,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 6.5032,
       "step": 18
+    },
+    {
+      "epoch": 0.03192702394526796,
+      "grad_norm": 1.3896228075027466,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.7985,
+      "step": 21
+    },
+    {
+      "epoch": 0.036488027366020526,
+      "grad_norm": 1.24579918384552,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.6393,
+      "step": 24
+    },
+    {
+      "epoch": 0.036488027366020526,
+      "eval_loss": 1.6593217849731445,
+      "eval_runtime": 31.7116,
+      "eval_samples_per_second": 8.735,
+      "eval_steps_per_second": 4.383,
+      "step": 24
+    },
+    {
+      "epoch": 0.04104903078677309,
+      "grad_norm": 1.1814146041870117,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.7082,
+      "step": 27
+    },
+    {
+      "epoch": 0.04561003420752566,
+      "grad_norm": 1.4193669557571411,
+      "learning_rate": 0.0,
+      "loss": 6.5813,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5211434118021120.0,
+  "total_flos": 7767986704220160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null