Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402c25695daab7181229ab35fa1132546de0138f7f9f9368dfcdcfc9fca0d843
+oid sha256:44bab1842dc1165b3d43a3d111bb1eefacd1891ca37fc57ffa0ca39a93199e15
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd450142a7f6434947b5af82049548223893344ad865377bbe1f5847888751f
+oid sha256:a535164f2323268b989df7dd1f7d6566f2705ea4498b0782e1c8853d9d6a60b3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45dceb42df4ae3cd9209e1c050954c116606848ce51da67405c222d6e3c939d5
+oid sha256:d4387c33c17d0a04a27329901554470ff486c8c8127dc0904fde5b379d8a9fe7
 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": 0.01030995968541405,
+  "epoch": 0.013217897032582117,
   "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": 0.1655,
       "step": 35
+    },
+    {
+      "epoch": 0.010574317626065692,
+      "grad_norm": 0.3092826008796692,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1545,
+      "step": 40
+    },
+    {
+      "epoch": 0.010574317626065692,
+      "eval_loss": 0.12997454404830933,
+      "eval_runtime": 252.0797,
+      "eval_samples_per_second": 6.319,
+      "eval_steps_per_second": 3.162,
+      "step": 40
+    },
+    {
+      "epoch": 0.011896107329323904,
+      "grad_norm": 0.38228216767311096,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1924,
+      "step": 45
+    },
+    {
+      "epoch": 0.013217897032582117,
+      "grad_norm": 0.350223183631897,
+      "learning_rate": 0.0,
+      "loss": 0.1116,
+      "step": 50
+    },
+    {
+      "epoch": 0.013217897032582117,
+      "eval_loss": 0.12738725543022156,
+      "eval_runtime": 251.7829,
+      "eval_samples_per_second": 6.327,
+      "eval_steps_per_second": 3.165,
+      "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": 8835877262327808.0,
+  "total_flos": 1.140113195139072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null