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:bd4503d16d5d4b0b3861d9b4482221daef5687e4ac143b2354e5783ba693d71c
+oid sha256:33bbbf485581f7862f908e2615ef3ed599e7ffec8ba2a4358c7457914d76cc47
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447d4078c3c85ecc1387b0e324fb2a9083966ca601a85f61a9eed8f6747e2233
+oid sha256:156248698d25561edca8a43626af677baa429d1474a84302a1848515e8ca9992
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
+oid sha256:dae2cff01f9b0fc3a44f22c10b61e1a8883cd6f6a47e470e57981350e6a19d5d
 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": 0.0006603482066889887,
+  "epoch": 0.0008466002649858829,
   "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": 6.9219,
       "step": 35
+    },
+    {
+      "epoch": 0.0006772802119887064,
+      "grad_norm": 0.2872024476528168,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.9202,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006772802119887064,
+      "eval_loss": 6.920102119445801,
+      "eval_runtime": 332.362,
+      "eval_samples_per_second": 74.822,
+      "eval_steps_per_second": 37.411,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007619402384872946,
+      "grad_norm": 0.2954590618610382,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9203,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008466002649858829,
+      "grad_norm": 0.3101924657821655,
+      "learning_rate": 0.0,
+      "loss": 6.9172,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008466002649858829,
+      "eval_loss": 6.919541835784912,
+      "eval_runtime": 339.0118,
+      "eval_samples_per_second": 73.354,
+      "eval_steps_per_second": 36.677,
+      "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": 66905266176.0,
+  "total_flos": 86350639104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null