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:c0e00c5c8f08a1516171dc25c374a7208caf7d05e7d3e251c7bc4d71f95e70bf
+oid sha256:71765f4bd7aec7547237ce4259f0d14944bf3e33805d809041f429364b18a54e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ed7ae54a18d914f396d62d7f01b413320826007ea445940dcf1095bfb5515f
+oid sha256:1b0189756ba7579f6e45a02f87a21971f99aa94c5442887c549c8b0e93c3d051
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.011380215932302306,
+  "epoch": 0.014590020426028597,
   "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": 1.2894,
       "step": 35
+    },
+    {
+      "epoch": 0.011672016340822877,
+      "grad_norm": 1.2051163911819458,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.192,
+      "step": 40
+    },
+    {
+      "epoch": 0.011672016340822877,
+      "eval_loss": 1.1521774530410767,
+      "eval_runtime": 354.0221,
+      "eval_samples_per_second": 4.076,
+      "eval_steps_per_second": 2.039,
+      "step": 40
+    },
+    {
+      "epoch": 0.013131018383425737,
+      "grad_norm": 0.819458544254303,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0784,
+      "step": 45
+    },
+    {
+      "epoch": 0.014590020426028597,
+      "grad_norm": 1.4205684661865234,
+      "learning_rate": 0.0,
+      "loss": 1.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.014590020426028597,
+      "eval_loss": 1.149507999420166,
+      "eval_runtime": 528.54,
+      "eval_samples_per_second": 2.73,
+      "eval_steps_per_second": 1.366,
+      "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": 1.4426601135538176e+16,
+  "total_flos": 1.84956424814592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null