Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95cd537b014738234d9c92874ac9ba1dd950b6079118241be47b0f10d27ce84
+oid sha256:81ca70464c6891920e1f1c6fe83db22bc0a91f7c7af8769d6b2121524c5f10b7
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1450084527cc85189315e4b94acaff8b5eb1b93aa0a96f5c2a280cc26886b99
+oid sha256:051d2b675f138dbfb7f1bacb7a389b85aedf2fb7a36e0e277db4b2e4320710ee
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0327c646fbcebdbfe58bb39ffa0aa64a521ffb921c8df37b9e57436d246f1866
+oid sha256:caa173be0daf3b70291aa54f3fc172b70d25960de7e9a07e7f57c5f27ae513c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8148b27980adb9b0bdd5c04049e531bfefcc05c06612ee72169cfb9b9fd7ee7
+oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06591957811470006,
+  "epoch": 0.13183915622940012,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 36.684,
       "eval_steps_per_second": 18.342,
       "step": 50
+    },
+    {
+      "epoch": 0.07910349373764008,
+      "grad_norm": 2.1022636890411377,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 1.2797,
+      "step": 60
+    },
+    {
+      "epoch": 0.0922874093605801,
+      "grad_norm": 2.0848679542541504,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3117,
+      "step": 70
+    },
+    {
+      "epoch": 0.1054713249835201,
+      "grad_norm": 2.1038565635681152,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 1.2998,
+      "step": 80
+    },
+    {
+      "epoch": 0.11865524060646011,
+      "grad_norm": 2.0592269897460938,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 1.3859,
+      "step": 90
+    },
+    {
+      "epoch": 0.13183915622940012,
+      "grad_norm": 1.9211629629135132,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 1.2282,
+      "step": 100
+    },
+    {
+      "epoch": 0.13183915622940012,
+      "eval_loss": 1.1935606002807617,
+      "eval_runtime": 4.3651,
+      "eval_samples_per_second": 36.654,
+      "eval_steps_per_second": 18.327,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2483537156505600.0,
+  "total_flos": 4967074313011200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null