Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb3f8ccedcd4fa0f74e709547ed8fe64624c281eba9e7bf7fa121d0ef7810e0
+oid sha256:d6374035612a146da1a109a61d39346ef90aa723c35c9a39d002c6f436b99e0f
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6b41dcbcbee0dfc9a1aaf53bcab5e8b6db24b28aa25d625d26d93dba01d685
+oid sha256:6043626bc4eaab3e567d8a690d89b2ba48bc4982f9614315e27098e503a238c6
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b27ce60eb7e6075b97db6b42dc9a41d4f94bd7192df0f418174df4eea3b94d
+oid sha256:bd90097bda2ff98046f4b0422fd3c485b996e564d7a8ece2d680b303573e27b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c99427ab0e3f179e8260c56d2a524955cd643e000ed1c4e3ac111dee56d825
+oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002949645340262659,
+  "epoch": 0.005899290680525318,
   "eval_steps": 63,
-  "global_step": 63,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 59.029,
       "eval_steps_per_second": 29.521,
       "step": 63
+    },
+    {
+      "epoch": 0.0032773837114029544,
+      "grad_norm": 4.394769668579102,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 3.894,
+      "step": 70
+    },
+    {
+      "epoch": 0.0037455813844605194,
+      "grad_norm": 3.7391180992126465,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 3.9238,
+      "step": 80
+    },
+    {
+      "epoch": 0.004213779057518084,
+      "grad_norm": 2.3897058963775635,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 4.0137,
+      "step": 90
+    },
+    {
+      "epoch": 0.004681976730575649,
+      "grad_norm": 3.922125816345215,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 3.9906,
+      "step": 100
+    },
+    {
+      "epoch": 0.005150174403633214,
+      "grad_norm": 3.0535309314727783,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 4.0744,
+      "step": 110
+    },
+    {
+      "epoch": 0.005618372076690779,
+      "grad_norm": 2.748141050338745,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 4.0713,
+      "step": 120
+    },
+    {
+      "epoch": 0.005899290680525318,
+      "eval_loss": 1.9673289060592651,
+      "eval_runtime": 76.3485,
+      "eval_samples_per_second": 58.901,
+      "eval_steps_per_second": 29.457,
+      "step": 126
     }
   ],
   "logging_steps": 10,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2056790369894400.0,
+  "total_flos": 4146228205977600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null