Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2258692e5ce1efb8773da5136ceb32cab834b24b0ccbf9f9c4ae9920d1952963
+oid sha256:973cf1aa0966368a7e6ba12d5ad5d422eae5357ae232b95494021cf4fc8fc4e1
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6301c1fdd180296b479b6467b981ee7b26f3f1f682a0298b3b0e313122b2efe8
+oid sha256:01028a66ed174d3f66fa94584c345641cb96d2b78b41dc9f75891e5599dc5c73
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.004579480405107882,
+  "epoch": 0.005871128724497285,
   "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": 10.3183,
       "step": 35
+    },
+    {
+      "epoch": 0.0046969029795978275,
+      "grad_norm": 0.3395172357559204,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3183,
+      "step": 40
+    },
+    {
+      "epoch": 0.0046969029795978275,
+      "eval_loss": 10.319413185119629,
+      "eval_runtime": 16.6745,
+      "eval_samples_per_second": 215.059,
+      "eval_steps_per_second": 107.53,
+      "step": 40
+    },
+    {
+      "epoch": 0.005284015852047556,
+      "grad_norm": 0.4023834764957428,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.316,
+      "step": 45
+    },
+    {
+      "epoch": 0.005871128724497285,
+      "grad_norm": 0.37457945942878723,
+      "learning_rate": 0.0,
+      "loss": 10.3167,
+      "step": 50
+    },
+    {
+      "epoch": 0.005871128724497285,
+      "eval_loss": 10.318948745727539,
+      "eval_runtime": 16.358,
+      "eval_samples_per_second": 219.22,
+      "eval_steps_per_second": 109.61,
+      "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": 507538145280.0,
+  "total_flos": 649778135040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null