Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e56cd6d84d6879aeae88cd346050b27fda0dd267096897a6da86dc49f98b557
+oid sha256:9f00157ec51ba7cc018774c27b48dd67894af9269bec8cc49a82db4e253c0f74
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a571171dd6e5ae46213776185e9a013b293f7d7bae37422ed1d54cde59584b05
+oid sha256:b5372244d3be5b258e7774e6726c02f36d9bdc60c39c049c7415a5091d3d3e0a
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d7af81722fc84004fda52a94ef8527f4a6ee2e50ba45e562bc8ecc44b205b0
+oid sha256:369b81b0fc696357288d516545d001fdfd60dd2370106c66d92e04ce565c9874
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024271844660194173,
+  "epoch": 0.0048543689320388345,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 4.524,
       "eval_steps_per_second": 2.263,
       "step": 15
+    },
+    {
+      "epoch": 0.002912621359223301,
+      "grad_norm": 2.2033326625823975,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.8597,
+      "step": 18
+    },
+    {
+      "epoch": 0.003236245954692557,
+      "eval_loss": 0.8138495683670044,
+      "eval_runtime": 573.2693,
+      "eval_samples_per_second": 4.541,
+      "eval_steps_per_second": 2.271,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033980582524271844,
+      "grad_norm": 1.6454766988754272,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8539,
+      "step": 21
+    },
+    {
+      "epoch": 0.003883495145631068,
+      "grad_norm": 1.1470767259597778,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6777,
+      "step": 24
+    },
+    {
+      "epoch": 0.0040453074433656954,
+      "eval_loss": 0.7886656522750854,
+      "eval_runtime": 575.3052,
+      "eval_samples_per_second": 4.525,
+      "eval_steps_per_second": 2.263,
+      "step": 25
+    },
+    {
+      "epoch": 0.004368932038834952,
+      "grad_norm": 1.2917059659957886,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.7204,
+      "step": 27
+    },
+    {
+      "epoch": 0.0048543689320388345,
+      "grad_norm": 0.9337906837463379,
+      "learning_rate": 0.0,
+      "loss": 0.6264,
+      "step": 30
+    },
+    {
+      "epoch": 0.0048543689320388345,
+      "eval_loss": 0.7828293442726135,
+      "eval_runtime": 574.2879,
+      "eval_samples_per_second": 4.533,
+      "eval_steps_per_second": 2.267,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5847569506762752.0,
+  "total_flos": 1.1791000808718336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null