Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306a8a7e54973801fd6ad56c59597fc3d526d2c00955e3043ae048a8d184e599
+oid sha256:f3288043eec7683df4e416d001357f8e489984d738a9c943b640c34ad7cc8f60
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffb5394229b0195f27605f79c1e114e4888db38ca381ee363ca292bb145840d
+oid sha256:4c7ee67ccd042e7312e40eaf00c625170d3aaee827a63fc72c56f5090da6347f
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a448c761d231bc0fb3f5b9140d4d36c6d5f57b2bc38a054844f026f5b0ed811b
+oid sha256:ad59a3ad9ee7bedb09ba7d97c2440bbe666df97975715a407e5fa6794e58b7f5
 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": 0.005418171714365101,
+  "epoch": 0.006946373992775771,
   "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": 1.117,
       "step": 35
+    },
+    {
+      "epoch": 0.005557099194220617,
+      "grad_norm": 3.183335304260254,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1804,
+      "step": 40
+    },
+    {
+      "epoch": 0.005557099194220617,
+      "eval_loss": 1.1752910614013672,
+      "eval_runtime": 246.4683,
+      "eval_samples_per_second": 12.298,
+      "eval_steps_per_second": 6.151,
+      "step": 40
+    },
+    {
+      "epoch": 0.006251736593498194,
+      "grad_norm": 2.3987159729003906,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1308,
+      "step": 45
+    },
+    {
+      "epoch": 0.006946373992775771,
+      "grad_norm": 2.901054620742798,
+      "learning_rate": 0.0,
+      "loss": 1.1039,
+      "step": 50
+    },
+    {
+      "epoch": 0.006946373992775771,
+      "eval_loss": 1.1731762886047363,
+      "eval_runtime": 246.5185,
+      "eval_samples_per_second": 12.295,
+      "eval_steps_per_second": 6.15,
+      "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": 4903664615424000.0,
+  "total_flos": 6211308512870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null