Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e09472efcaed6e84613c673e93e768daa15e0347dac83d6faaf7cb646bf048
+oid sha256:77e5dc83a78cc6351fc32637d71a9dacbd131ab66345f6d2f8f749c853b27d3d
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4932af9e71341a96c77820a70e56a76c1dd937a1666d7a9b7a78b97bfc64e7e4
+oid sha256:4f5f5574e71a10177ab3c442f8a58973abbed2c720d94e4899eacb3728199c70
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c10ee58f8233b8536540a132a55344cb7a8dbf4099e7f740aa7b7f73a9c382
+oid sha256:e0d3d8a304ab1ed0f3ec7b9914e2adb54aa2de09e3b6ee9e57aa48c597841289
 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": 0.006910911265671378,
+  "epoch": 0.008860142648296638,
   "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": 16.444,
       "step": 35
+    },
+    {
+      "epoch": 0.0070881141186373104,
+      "grad_norm": 85.38540649414062,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 16.5072,
+      "step": 40
+    },
+    {
+      "epoch": 0.0070881141186373104,
+      "eval_loss": 4.078617095947266,
+      "eval_runtime": 50.6748,
+      "eval_samples_per_second": 46.907,
+      "eval_steps_per_second": 23.463,
+      "step": 40
+    },
+    {
+      "epoch": 0.007974128383466974,
+      "grad_norm": 77.00909423828125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 16.4525,
+      "step": 45
+    },
+    {
+      "epoch": 0.008860142648296638,
+      "grad_norm": 109.96552276611328,
+      "learning_rate": 0.0,
+      "loss": 16.0889,
+      "step": 50
+    },
+    {
+      "epoch": 0.008860142648296638,
+      "eval_loss": 4.0669474601745605,
+      "eval_runtime": 50.28,
+      "eval_samples_per_second": 47.275,
+      "eval_steps_per_second": 23.648,
+      "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": 471541041070080.0,
+  "total_flos": 611906746318848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null