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:f08e2bc3b719745a9e91095aae53d13c3ae11d96ba9deeeb409ba615eaeebc54
+oid sha256:7895496fc5e2dd7af62801f82dfcc481b73ad0e72866d06d72ec8975f4743e5b
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d9afa8a3bb4a7620179fc7db72f98d57f6b729de28a708fc26b5d95c8f48f4
+oid sha256:11e996b4653a998ca674c5842e0749dfcc0653453121fde1e17d7d9d091a77fe
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b690cc0be3f085e7988aab186ba333a6d5ce3dea047c99159f04ae1d28d68308
+oid sha256:e53a9ca55b33a0bdef1579ef84ca0c64f3e10ffef611f251afa965dc36bf6561
 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": 0.0049665711556829036,
+  "epoch": 0.006367398917542184,
   "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": 1.7372,
       "step": 35
+    },
+    {
+      "epoch": 0.005093919134033747,
+      "grad_norm": 0.9296777248382568,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5463,
+      "step": 40
+    },
+    {
+      "epoch": 0.005093919134033747,
+      "eval_loss": 2.25455641746521,
+      "eval_runtime": 163.7581,
+      "eval_samples_per_second": 20.194,
+      "eval_steps_per_second": 10.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.0057306590257879654,
+      "grad_norm": 0.7359820008277893,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7395,
+      "step": 45
+    },
+    {
+      "epoch": 0.006367398917542184,
+      "grad_norm": 1.552220106124878,
+      "learning_rate": 0.0,
+      "loss": 1.9366,
+      "step": 50
+    },
+    {
+      "epoch": 0.006367398917542184,
+      "eval_loss": 2.252518892288208,
+      "eval_runtime": 165.9093,
+      "eval_samples_per_second": 19.933,
+      "eval_steps_per_second": 9.969,
+      "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": 3322077543137280.0,
+  "total_flos": 4209124426383360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null