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:c46b401b3f707d84397164404189f29f1670e1efec00c3b70d2d4c0d5a426f7a
+oid sha256:a089527d4e7665bb4ea1649628933fd32f18f13444139d3b05f11dee1b102591
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b2e407c4de7d2133f11659d4a7c205cbc0975219e278ea6d21d0c04ad8da17
+oid sha256:115af964900a47c2459d70b5d6fd97ead2fb1e9830be2e8e23de503dc7ec081f
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40337e495d1219cb3d2e8594d3017fd597c4ba51cb0f0b5fe566fc1e74f6a899
+oid sha256:051441c0d1f3054eeb7899fd93badd8ad7ba2c02f0bffcf5fb8a3c5c459aeae9
 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": 0.009275003864584944,
+  "epoch": 0.018550007729169888,
   "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": 2.197,
       "eval_steps_per_second": 1.1,
       "step": 15
+    },
+    {
+      "epoch": 0.011130004637501932,
+      "grad_norm": 3.3581345081329346,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 7.2519,
+      "step": 18
+    },
+    {
+      "epoch": 0.012366671819446591,
+      "eval_loss": 1.7316858768463135,
+      "eval_runtime": 310.1422,
+      "eval_samples_per_second": 2.196,
+      "eval_steps_per_second": 1.099,
+      "step": 20
+    },
+    {
+      "epoch": 0.01298500541041892,
+      "grad_norm": 3.1908483505249023,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4249,
+      "step": 21
+    },
+    {
+      "epoch": 0.01484000618333591,
+      "grad_norm": 3.0952506065368652,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.6318,
+      "step": 24
+    },
+    {
+      "epoch": 0.015458339774308239,
+      "eval_loss": 1.6776248216629028,
+      "eval_runtime": 309.8368,
+      "eval_samples_per_second": 2.198,
+      "eval_steps_per_second": 1.101,
+      "step": 25
+    },
+    {
+      "epoch": 0.016695006956252898,
+      "grad_norm": 2.567011594772339,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 6.661,
+      "step": 27
+    },
+    {
+      "epoch": 0.018550007729169888,
+      "grad_norm": 3.4367024898529053,
+      "learning_rate": 0.0,
+      "loss": 6.1231,
+      "step": 30
+    },
+    {
+      "epoch": 0.018550007729169888,
+      "eval_loss": 1.6673802137374878,
+      "eval_runtime": 309.8189,
+      "eval_samples_per_second": 2.198,
+      "eval_steps_per_second": 1.101,
+      "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": 9521744943513600.0,
+  "total_flos": 1.920218563608576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null