Training in progress, step 21, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49dbdc51a749f4586f4bfc5c29f962254bc2481435b9b40b18ff54b41afdeaf
+oid sha256:1ffcbfa7a884b5ee2be85fe02a62d94a208014d00fcfac937cb0f5bdb36cd3b3
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051d7de4ca8ec489f06051a5cac9473ba046b56d064e63e01d60fef33aa00efb
+oid sha256:d9c74c0a9cfc41d4815ebdb27f26dcaa89e187953e456359fd7b4b6b402b4891
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585fddc4777b08565c6c3d5891526e512f43b18c6849f7dfec648d08d9b7a952
+oid sha256:4fe962ac8858c52820b482a66d763fc79f2e273957b46d995fb4455aba4929bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94bcb770032d6a31492d829aa0341ce1de94ff1ad97397c70c01125f6cf0767
+oid sha256:d8fae250b15c396253340cf1fca6b06fc7e3360266084e6b572fe269086e601a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5714285714285714,
+  "epoch": 0.8571428571428571,
   "eval_steps": 5,
-  "global_step": 14,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,29 @@
       "eval_samples_per_second": 99.68,
       "eval_steps_per_second": 12.687,
       "step": 10
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "eval_loss": 11.865002632141113,
+      "eval_runtime": 1.6738,
+      "eval_samples_per_second": 98.576,
+      "eval_steps_per_second": 12.546,
+      "step": 15
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.5802960395812988,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 11.8687,
+      "step": 20
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "eval_loss": 11.86227035522461,
+      "eval_runtime": 1.6443,
+      "eval_samples_per_second": 100.347,
+      "eval_steps_per_second": 12.771,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -57,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 55694390722560.0,
+  "total_flos": 83103540314112.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null