Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d6278f482f33ce60bedccb71eaf12f26488a5149825ddbba74bd0b34ff5541
+oid sha256:5e83055ae268927f03c10b0f1b8e06433b2b90ac702e48ed8ac3638fa14503af
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4520c6c09c2738656aedf5835599fccd4f2060b415ca79285196ca6af9af4c5c
+oid sha256:a0253101e501d0989655215f014de0e13a9b7972eba29d473a3fc90c31a5dbd0
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b073eae0856d95a78bd1210e484de480f18e699d417df6566c139d5389912738
+oid sha256:e2edc0261f7034ce0d71cea4f289a97e7923584b1d4870351bbf4900337528d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28421052631578947,
+  "epoch": 0.37593984962406013,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 373.281,
       "eval_steps_per_second": 186.64,
       "step": 189
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.28547802567481995,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 10.3431,
+      "step": 190
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 0.15805752575397491,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 10.3395,
+      "step": 200
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.14654022455215454,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 10.3429,
+      "step": 210
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 0.13083398342132568,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 10.3441,
+      "step": 220
+    },
+    {
+      "epoch": 0.3458646616541353,
+      "grad_norm": 0.2036089301109314,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 10.3387,
+      "step": 230
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 0.13818128407001495,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 10.3463,
+      "step": 240
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 0.20554596185684204,
+      "learning_rate": 0.0,
+      "loss": 10.3422,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1235645300736.0,
+  "total_flos": 1634451456000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null