Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6646e9514e5467d7d21d33b433925a16848e388d07230f17ff5a13d68a8845cf
+oid sha256:c4975f68b906d98810a68c45b5e13a7ea574d3176e2d18f5e620ef8c2f3ef854
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7912d43696f29062ade59734a1ad37295676a9db4810f7af7263e1797617f1
+oid sha256:216300f854455eee09ff411cfc0d21bbd12e859346f910ccc9f3a47e644c8348
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c60f4422bc1f8e51f57e103c814eb2ca99f436a4f28999c9c00667a5df963cb
+oid sha256:a2ba7452774c46e086497d4079101b00ed5fd868073e4d7e9ab10329813ff42e
 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": 0.001060585973750497,
+  "epoch": 0.0015908789606257458,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 225.454,
       "eval_steps_per_second": 112.727,
       "step": 20
+    },
+    {
+      "epoch": 0.001113615272438022,
+      "grad_norm": 1518.35986328125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 45.4035,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012727031685005965,
+      "grad_norm": 1333.44287109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 49.1836,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013257324671881213,
+      "eval_loss": 11.057934761047363,
+      "eval_runtime": 35.4103,
+      "eval_samples_per_second": 224.228,
+      "eval_steps_per_second": 112.114,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014317910645631712,
+      "grad_norm": 1666.79833984375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 43.5465,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015908789606257458,
+      "grad_norm": 2032.2802734375,
+      "learning_rate": 0.0,
+      "loss": 42.8751,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015908789606257458,
+      "eval_loss": 11.05472469329834,
+      "eval_runtime": 35.3871,
+      "eval_samples_per_second": 224.376,
+      "eval_steps_per_second": 112.188,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 44686450360320.0,
+  "total_flos": 67029675540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null