Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096f9770877eea438ca2c8f9d35c4045489d98c5bdce2d65639c988ae12bb12d
+oid sha256:4f6e1ca3876185b56aad9455ddbbea04bb82ed4536a7f7b2ea11207c765d51ee
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a69894bd828229316850146e97eb91b07eb178d4fe69cfd57b471bd04ed78f7
+oid sha256:416b35602685895d3cc19a4f262b080b80b7c6efd692ec70750c3b488e026b1b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2ee68b7a1edf1ee81c51eec607d22df2583032538d516731253af350bcbe87
+oid sha256:e3f0a2454d3233fd98ce4aff2676a014daaea94e489cc09b1e2581c2187e482b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016519823788546256,
+  "epoch": 0.03303964757709251,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 2.92,
       "eval_steps_per_second": 1.464,
       "step": 15
+    },
+    {
+      "epoch": 0.019823788546255508,
+      "grad_norm": 0.5499920845031738,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.8033,
+      "step": 18
+    },
+    {
+      "epoch": 0.022026431718061675,
+      "eval_loss": 0.6734703779220581,
+      "eval_runtime": 131.2,
+      "eval_samples_per_second": 2.919,
+      "eval_steps_per_second": 1.463,
+      "step": 20
+    },
+    {
+      "epoch": 0.023127753303964757,
+      "grad_norm": 0.36365655064582825,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6383,
+      "step": 21
+    },
+    {
+      "epoch": 0.02643171806167401,
+      "grad_norm": 0.3813054859638214,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6955,
+      "step": 24
+    },
+    {
+      "epoch": 0.02753303964757709,
+      "eval_loss": 0.6509636640548706,
+      "eval_runtime": 131.2701,
+      "eval_samples_per_second": 2.918,
+      "eval_steps_per_second": 1.463,
+      "step": 25
+    },
+    {
+      "epoch": 0.02973568281938326,
+      "grad_norm": 0.4139375388622284,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5708,
+      "step": 27
+    },
+    {
+      "epoch": 0.03303964757709251,
+      "grad_norm": 0.3623638153076172,
+      "learning_rate": 0.0,
+      "loss": 0.6539,
+      "step": 30
+    },
+    {
+      "epoch": 0.03303964757709251,
+      "eval_loss": 0.6442951560020447,
+      "eval_runtime": 131.0953,
+      "eval_samples_per_second": 2.922,
+      "eval_steps_per_second": 1.465,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0943027484819456e+16,
+  "total_flos": 2.1515104885407744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null