Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d076565d9cb95de0e40e01e9b4d08ef5c9404424e6e36d5080ad48fa8633439
+oid sha256:b936be5e55dd2706709b3f3a9f106c8ba911aaa61434846e40249cd23300d7e2
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1ebee2cefd7869f29b6a105f2817b88674d22e55c33066fe224251c5f05137
+oid sha256:dcc54184f86ce9ed2955931cd61d1894d9fc5876e388d0ce3b4127257013d65f
 size 115438

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65371c2904759f76162cc4aca108fabf7035f3230ba0d5e1b8e3027168e13f5
+oid sha256:b73b43b2e6e7654f681327fbc9d8864ac66d7432ad9f407444f6bf6170764eb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0332409972299169,
+  "epoch": 0.0443213296398892,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 246.716,
       "eval_steps_per_second": 123.358,
       "step": 15
+    },
+    {
+      "epoch": 0.03545706371191136,
+      "grad_norm": 0.6504232287406921,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.9152,
+      "step": 16
+    },
+    {
+      "epoch": 0.037673130193905814,
+      "grad_norm": 0.791231632232666,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.8909,
+      "step": 17
+    },
+    {
+      "epoch": 0.039889196675900275,
+      "grad_norm": 0.7693294882774353,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 6.883,
+      "step": 18
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.7056183815002441,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 6.8989,
+      "step": 19
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "grad_norm": 0.7791154384613037,
+      "learning_rate": 0.0,
+      "loss": 6.8869,
+      "step": 20
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "eval_loss": 6.881771564483643,
+      "eval_runtime": 0.7678,
+      "eval_samples_per_second": 247.475,
+      "eval_steps_per_second": 123.737,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 95761735680.0,
+  "total_flos": 125226885120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null