Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f879fe833a6e69817a274d1e4ab362507d3d5abfae7d359f65d06193d96d38
+oid sha256:e1a6ce8bdde68f6bc5845ed9911025f5634332dc5f8c74b597216401dfcee66d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7940756b4f90768ec46355edf3d4adf3415cd01bc902621d4ec9da86aceecf7b
+oid sha256:05ab88b55e6993adf3ac16b8abc1ebb17a2b5e32051e4eb8e389f77fc277b212
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79860259ff731f0b1c006300fee3fbd1e0fb1cad375751b62eee5d8cabbc13f0
+oid sha256:b9b32a31b90c640b6f3edbb6f5edfd55f2a05c8f726be41404fdb7ef23099e0b
 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": 0.01845062093435837,
+  "epoch": 0.02365464222353637,
   "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": 1.4231,
       "step": 35
+    },
+    {
+      "epoch": 0.018923713778829097,
+      "grad_norm": 2.7728047370910645,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2891,
+      "step": 40
+    },
+    {
+      "epoch": 0.018923713778829097,
+      "eval_loss": 1.441538691520691,
+      "eval_runtime": 60.8695,
+      "eval_samples_per_second": 14.621,
+      "eval_steps_per_second": 7.311,
+      "step": 40
+    },
+    {
+      "epoch": 0.021289178001182733,
+      "grad_norm": 2.58444881439209,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2203,
+      "step": 45
+    },
+    {
+      "epoch": 0.02365464222353637,
+      "grad_norm": 2.4740593433380127,
+      "learning_rate": 0.0,
+      "loss": 1.4042,
+      "step": 50
+    },
+    {
+      "epoch": 0.02365464222353637,
+      "eval_loss": 1.433903455734253,
+      "eval_runtime": 60.7074,
+      "eval_samples_per_second": 14.66,
+      "eval_steps_per_second": 7.33,
+      "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": 7259539673972736.0,
+  "total_flos": 9294060346933248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null