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:e32264a2a885aa27a0aa96ce9f09b78b305bd715aee8d9c92de828bc0caac8ff
+oid sha256:f36ce4932b1ac30377e580c914de68861c6acc64ebd378e3e89ab699d5812b62
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104f14af17cda8d0007171226780c1d4ab0668d8b2b9fe4fdf33bc489866df5a
+oid sha256:ac9eba37c5c64e4092d17ffc8f2bfe95d7f562f037ef014d891c9edf6121862c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee089b8eda3d2f03579660229909140f9bb3bc7af0a9129bb3775da6328a203
+oid sha256:6beb92e82d89b74efdd456fb9bf2b41610797ca90b007f020dc4fb8145708801
 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": 0.0029412319236788026,
+  "epoch": 0.003770810158562567,
   "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": 0.5669,
       "step": 35
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "grad_norm": 1.386945128440857,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.53,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "eval_loss": 0.5142520070075989,
+      "eval_runtime": 657.6286,
+      "eval_samples_per_second": 8.491,
+      "eval_steps_per_second": 4.246,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033937291427063106,
+      "grad_norm": 2.1587717533111572,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4441,
+      "step": 45
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "grad_norm": 1.3008843660354614,
+      "learning_rate": 0.0,
+      "loss": 0.4892,
+      "step": 50
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "eval_loss": 0.5087710022926331,
+      "eval_runtime": 658.2197,
+      "eval_samples_per_second": 8.483,
+      "eval_steps_per_second": 4.242,
+      "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": 1.3964210073501696e+16,
+  "total_flos": 1.780205588840448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null