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:e9f184bd8eab2718597e454ee47284182973f744ff14e0d1c875f166a10937d3
+oid sha256:71d34c9d1f070921cf20112f805cbd861af21c5b989b1ba8e1ca784639634e52
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1daf0dece60de4e596c08e57e10afffc71a2a9152a45236429f0e3be749449a
+oid sha256:48700a2739ccc212045d9727ddba31823fb8b9fd96436bfb9ddbbb61e2f8651d
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457548b77ed5d7703d69eacdc9aca9fe710c41943f0b7a77991d95d5848083b0
+oid sha256:5fd8f0a7245c19e9d58956653f1a0c1b27d3beb55f73133fe59b9f074e10fba6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02437538086532602,
+  "epoch": 0.04875076173065204,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,116 @@
       "eval_samples_per_second": 3.955,
       "eval_steps_per_second": 1.989,
       "step": 10
+    },
+    {
+      "epoch": 0.02681291895185862,
+      "grad_norm": 1.2626514434814453,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.1281,
+      "step": 11
+    },
+    {
+      "epoch": 0.029250457038391225,
+      "grad_norm": 1.1027222871780396,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.8334,
+      "step": 12
+    },
+    {
+      "epoch": 0.029250457038391225,
+      "eval_loss": 1.4252070188522339,
+      "eval_runtime": 43.6162,
+      "eval_samples_per_second": 3.966,
+      "eval_steps_per_second": 1.995,
+      "step": 12
+    },
+    {
+      "epoch": 0.031687995124923825,
+      "grad_norm": 1.4160807132720947,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 1.2873,
+      "step": 13
+    },
+    {
+      "epoch": 0.03412553321145643,
+      "grad_norm": 1.6689919233322144,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0563,
+      "step": 14
+    },
+    {
+      "epoch": 0.03412553321145643,
+      "eval_loss": 1.3921422958374023,
+      "eval_runtime": 43.7862,
+      "eval_samples_per_second": 3.951,
+      "eval_steps_per_second": 1.987,
+      "step": 14
+    },
+    {
+      "epoch": 0.03656307129798903,
+      "grad_norm": 1.5969661474227905,
+      "learning_rate": 0.0001,
+      "loss": 1.117,
+      "step": 15
+    },
+    {
+      "epoch": 0.039000609384521635,
+      "grad_norm": 2.8356218338012695,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3988,
+      "step": 16
+    },
+    {
+      "epoch": 0.039000609384521635,
+      "eval_loss": 1.360350251197815,
+      "eval_runtime": 43.6174,
+      "eval_samples_per_second": 3.966,
+      "eval_steps_per_second": 1.995,
+      "step": 16
+    },
+    {
+      "epoch": 0.04143814747105423,
+      "grad_norm": 1.8324129581451416,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.4755,
+      "step": 17
+    },
+    {
+      "epoch": 0.043875685557586835,
+      "grad_norm": 1.618000864982605,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9456,
+      "step": 18
+    },
+    {
+      "epoch": 0.043875685557586835,
+      "eval_loss": 1.3482810258865356,
+      "eval_runtime": 43.6176,
+      "eval_samples_per_second": 3.966,
+      "eval_steps_per_second": 1.995,
+      "step": 18
+    },
+    {
+      "epoch": 0.04631322364411944,
+      "grad_norm": 1.9570136070251465,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.34,
+      "step": 19
+    },
+    {
+      "epoch": 0.04875076173065204,
+      "grad_norm": 1.8460969924926758,
+      "learning_rate": 0.0,
+      "loss": 1.46,
+      "step": 20
+    },
+    {
+      "epoch": 0.04875076173065204,
+      "eval_loss": 1.3457626104354858,
+      "eval_runtime": 43.686,
+      "eval_samples_per_second": 3.96,
+      "eval_steps_per_second": 1.991,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -139,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7398256992583680.0,
+  "total_flos": 1.479651398516736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null