Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8793f46feb5de8084edfe2d09eb7051d2e0cf0226d4c35f19c7f3b706f020162
+oid sha256:9fcf40be826f55b07270198e0a6ead902a546dedd458e282c2ffd682c7f06eaa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81abc551906a3c2b0ee0bcf4e2f4b1fae525647218995a2d644aa121904655c5
+oid sha256:4eceac72edacc47b86aa1b6436a39c3f9c719c923b943c1c6d4b1f803e72ffbd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42700a3931f169d1a7cb24ca5c5bfdf8c30401d4efdc7d55be9e5bed753e25b1
+oid sha256:dd3b0103484cbe9033aa207b10c52e72e6e07124b9b9355e171cb765f0460e37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cedaf8893734b19717a3bbbc716629d55965a18bdde504cf46d9182fcb60eb14
+oid sha256:666e3907648b0318630be4f0e9270d7d902986930986134493537abd333e959c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014670823399963322,
+  "epoch": 0.017115960633290545,
   "eval_steps": 34,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -225,6 +225,49 @@
       "learning_rate": 0.0002,
       "loss": 1.0082,
       "step": 30
+    },
+    {
+      "epoch": 0.015159850846628768,
+      "grad_norm": 0.47625860571861267,
+      "learning_rate": 0.00019998292504580528,
+      "loss": 0.9419,
+      "step": 31
+    },
+    {
+      "epoch": 0.01564887829329421,
+      "grad_norm": 0.5290003418922424,
+      "learning_rate": 0.0001999317060143023,
+      "loss": 1.1635,
+      "step": 32
+    },
+    {
+      "epoch": 0.016137905739959654,
+      "grad_norm": 0.5592769980430603,
+      "learning_rate": 0.0001998463603967434,
+      "loss": 0.9437,
+      "step": 33
+    },
+    {
+      "epoch": 0.0166269331866251,
+      "grad_norm": 0.3583241403102875,
+      "learning_rate": 0.00019972691733857883,
+      "loss": 1.1428,
+      "step": 34
+    },
+    {
+      "epoch": 0.0166269331866251,
+      "eval_loss": 1.0231887102127075,
+      "eval_runtime": 1359.3297,
+      "eval_samples_per_second": 1.9,
+      "eval_steps_per_second": 0.633,
+      "step": 34
+    },
+    {
+      "epoch": 0.017115960633290545,
+      "grad_norm": 0.41851457953453064,
+      "learning_rate": 0.00019957341762950344,
+      "loss": 1.0976,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -244,7 +287,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3316862586650624e+17,
+  "total_flos": 1.5536339684425728e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null