Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00105599e1b5f1bd9ebde93f5e94fde41bc3f0e2344b31a16b9b76e1e3add8c
+oid sha256:1af76e1e0dd00a9f59b6ff10ca1e1f42bbb8ba6922120b592df4c237087236c8
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5476d8276a6ea182f7fe7c00336afd3a7842f0ec1fe27ad73960a09c77368181
+oid sha256:a8edb6d38a927417a5bf42f730ec299d379a19310b770c90e87b13b71ad8bc4f
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70febbcd5a32ad1fbfb47689f303006e4c5b98f4d8089822684ffffea406a65
+oid sha256:1bc95aa1fa7dde95ac6ad02afc6ad4500983da0c805a0135f524d22566a1f0ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c8ce389652c7905c49d38747ca9a7fa7280b6303b132da4eaaf73debfbf397
+oid sha256:a8d3fb6d75450a0bf8b65472e12a8bd1750514e7448c88ea9c5cf839154f984b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012894906511927788,
+  "epoch": 0.025789813023855575,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,81 @@
       "eval_samples_per_second": 6.881,
       "eval_steps_per_second": 3.44,
       "step": 5
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "grad_norm": 0.6461398601531982,
+      "learning_rate": 0.0006,
+      "loss": 0.8245,
+      "step": 6
+    },
+    {
+      "epoch": 0.015473887814313346,
+      "eval_loss": 0.9021034240722656,
+      "eval_runtime": 23.8587,
+      "eval_samples_per_second": 6.874,
+      "eval_steps_per_second": 3.437,
+      "step": 6
+    },
+    {
+      "epoch": 0.018052869116698903,
+      "grad_norm": 0.6693152785301208,
+      "learning_rate": 0.0007,
+      "loss": 0.8799,
+      "step": 7
+    },
+    {
+      "epoch": 0.018052869116698903,
+      "eval_loss": 0.8947257995605469,
+      "eval_runtime": 23.8583,
+      "eval_samples_per_second": 6.874,
+      "eval_steps_per_second": 3.437,
+      "step": 7
+    },
+    {
+      "epoch": 0.020631850419084462,
+      "grad_norm": 0.8548164367675781,
+      "learning_rate": 0.0008,
+      "loss": 0.7926,
+      "step": 8
+    },
+    {
+      "epoch": 0.020631850419084462,
+      "eval_loss": 0.8847903609275818,
+      "eval_runtime": 23.8385,
+      "eval_samples_per_second": 6.88,
+      "eval_steps_per_second": 3.44,
+      "step": 8
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "grad_norm": 0.6702899932861328,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.9324,
+      "step": 9
+    },
+    {
+      "epoch": 0.02321083172147002,
+      "eval_loss": 0.8762988448143005,
+      "eval_runtime": 23.8478,
+      "eval_samples_per_second": 6.877,
+      "eval_steps_per_second": 3.438,
+      "step": 9
+    },
+    {
+      "epoch": 0.025789813023855575,
+      "grad_norm": 0.7006492018699646,
+      "learning_rate": 0.001,
+      "loss": 0.8441,
+      "step": 10
+    },
+    {
+      "epoch": 0.025789813023855575,
+      "eval_loss": 0.8688957691192627,
+      "eval_runtime": 23.8639,
+      "eval_samples_per_second": 6.872,
+      "eval_steps_per_second": 3.436,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -96,12 +171,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null