Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2995f781ed74f3377cbedb73668f4c2604d96c9fb2489dd59eda4288302bd7
+oid sha256:540695a3a9f43d9bbd1ef789d552460b8c74b46bd4fe758079e6157729c7e2ec
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df16017fc50b7c065b86c7bafca727334d4e926f8dbad3e150d972f1bd5cce0
+oid sha256:fa7428b52cb33a82912bb70cd558b2213508ff4ab07a0f854523e513b35a9f53
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10afebc62f6c8e891ad93ef14a7ba50b2c58f0717580ad02c0baad1acebe56b0
+oid sha256:a808482866d58c57fe0290015fc20e4f8b8939db7d59d8f55d0fcd2b8b4cf266
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd734c499cbd9269039444aa61a9c5a6fbae1cfe5ae2a2f523c9e7a6137392e
+oid sha256:56e49a8262b2a61d3153e5d379c20cfb08094371d950647117ad67ae4b87231f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.5,
   "eval_steps": 24,
-  "global_step": 24,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,70 @@
       "eval_samples_per_second": 48.78,
       "eval_steps_per_second": 6.323,
       "step": 24
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.2701338827610016,
+      "learning_rate": 4.954008042777125e-05,
+      "loss": 1.666,
+      "step": 27
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.35075831413269043,
+      "learning_rate": 4.93641851874178e-05,
+      "loss": 1.6302,
+      "step": 30
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.31512945890426636,
+      "learning_rate": 4.916028962942762e-05,
+      "loss": 1.6324,
+      "step": 33
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.2673735022544861,
+      "learning_rate": 4.892862807891131e-05,
+      "loss": 1.5973,
+      "step": 36
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.27960431575775146,
+      "learning_rate": 4.866946677079314e-05,
+      "loss": 1.5657,
+      "step": 39
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.3442665934562683,
+      "learning_rate": 4.8383103543843036e-05,
+      "loss": 1.564,
+      "step": 42
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.3022296130657196,
+      "learning_rate": 4.806986749838807e-05,
+      "loss": 1.557,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.30464908480644226,
+      "learning_rate": 4.773011861809693e-05,
+      "loss": 1.5419,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.552250862121582,
+      "eval_runtime": 3.3169,
+      "eval_samples_per_second": 48.84,
+      "eval_steps_per_second": 6.331,
+      "step": 48
     }
   ],
   "logging_steps": 3,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5439527023804416.0,
+  "total_flos": 1.06657392623616e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null