Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2318934a559574d1d5ffe858353051e44e9a0f98bfcec895a212d5b83e23a6fb
+oid sha256:fdd6def2437d6b11a46f29978b2e4e44873b9d24ae5221149e8f6a7a347a166f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a501e9af8031271f08e11252a83c842fc40ce0f1d5f2bc52866f5bb66073df0
+oid sha256:038f61e59d93d2a58a2b8f59871a56ae7a6dbe38a28a67ba28d6a793b220a771
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81d341293548ca00e0e58d5d96dd5b9a987f30f65d8d779264a3bcee6bef50b4
+oid sha256:e01c28df0e74f379f11a5bc69777121dc7b9c14b90ffd176758e1c14035ca1d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1013299556681444,
+  "epoch": 0.1266624445851805,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 5.000000000000002e-05,
       "loss": 0.0566,
       "step": 20
+    },
+    {
+      "epoch": 0.10639645345155162,
+      "grad_norm": 0.8825861811637878,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.056,
+      "step": 21
+    },
+    {
+      "epoch": 0.10639645345155162,
+      "eval_loss": 0.13038882613182068,
+      "eval_runtime": 17.2129,
+      "eval_samples_per_second": 9.702,
+      "eval_steps_per_second": 4.88,
+      "step": 21
+    },
+    {
+      "epoch": 0.11146295123495883,
+      "grad_norm": 0.5869631171226501,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0261,
+      "step": 22
+    },
+    {
+      "epoch": 0.11652944901836605,
+      "grad_norm": 0.7820150852203369,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0398,
+      "step": 23
+    },
+    {
+      "epoch": 0.12159594680177327,
+      "grad_norm": 0.20869500935077667,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0073,
+      "step": 24
+    },
+    {
+      "epoch": 0.12159594680177327,
+      "eval_loss": 0.129783034324646,
+      "eval_runtime": 17.2227,
+      "eval_samples_per_second": 9.696,
+      "eval_steps_per_second": 4.877,
+      "step": 24
+    },
+    {
+      "epoch": 0.1266624445851805,
+      "grad_norm": 0.2913738489151001,
+      "learning_rate": 0.0,
+      "loss": 0.01,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.64437646753792e+16,
+  "total_flos": 3.3054705844224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null