Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1371ecb6d32929f20cfdc17b80b405ba5a32115346d140c6708390270d0b56a8
+oid sha256:d11265525d941b1924c0c6e043d19eae35c3be46943a61f51832ac8dc39166e1
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1dce1e0bcc55dd0e9162029ed9d6f81cf08e063d17d5079eaba957ebd704180
+oid sha256:40d749e3395da0bd219a4228df12a0f17d18a84fee67a764d0ac2a461b6587fc
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295480827c70f9cd2cc957f5b4871246e7a40e8362f8bcbf2ee121f8124e0e12
+oid sha256:2ac917533a416b3e4249f121a4cbee63e74b6272b8a8995a8e760c083b27676b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008163098712271178,
+  "epoch": 0.0012244648068406767,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.6754,
       "step": 18
+    },
+    {
+      "epoch": 0.0008571253647884737,
+      "grad_norm": 1.1784299612045288,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.7099,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009795718454725414,
+      "grad_norm": 1.3243367671966553,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.6013,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009795718454725414,
+      "eval_loss": 1.684644103050232,
+      "eval_runtime": 667.3504,
+      "eval_samples_per_second": 15.458,
+      "eval_steps_per_second": 7.729,
+      "step": 24
+    },
+    {
+      "epoch": 0.001102018326156609,
+      "grad_norm": 1.1877875328063965,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.6743,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012244648068406767,
+      "grad_norm": 1.2480648756027222,
+      "learning_rate": 0.0,
+      "loss": 1.6012,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null