Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9972df20591cbf0f4b4dc4627e7c78e9c2b89487664047eb5921290f11ed9824
+oid sha256:38b671df8875e3a0387626590bc736441a740f1c1ed6a76a9c3a3790a5e6a272
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af078577ff448760fa82619643520097f4c259bde8dd470374b2586c7d037abb
+oid sha256:59322eeedd22ebd9449d471aa83b6e6970e678c23836c78040623cc5f9521124
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399171def2779bd0a4edea00ec815fe9bfd7f86cec979b7ea47ed048203a9783
+oid sha256:c537aa87f7577d8e8b0e29869b2ff3e03ca4ffd7c2022629871808b17fa6a30b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45023449713392394,
+  "epoch": 0.6003126628452319,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 118.649,
       "eval_steps_per_second": 59.617,
       "step": 27
+    },
+    {
+      "epoch": 0.5002605523710266,
+      "grad_norm": 0.05109262466430664,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 11.7588,
+      "step": 30
+    },
+    {
+      "epoch": 0.5502866076081292,
+      "grad_norm": 0.06546574831008911,
+      "learning_rate": 0.0001404372005304598,
+      "loss": 11.7578,
+      "step": 33
+    },
+    {
+      "epoch": 0.6003126628452319,
+      "grad_norm": 0.06636377424001694,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 11.7557,
+      "step": 36
+    },
+    {
+      "epoch": 0.6003126628452319,
+      "eval_loss": 11.755020141601562,
+      "eval_runtime": 1.7074,
+      "eval_samples_per_second": 118.891,
+      "eval_steps_per_second": 59.738,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 50241343979520.0,
+  "total_flos": 67142101893120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null