Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8d2fb97b1177dca02d62da86c52decec2811fa28f4aa72e458c3d25b80f9a2
+oid sha256:77c4d6621d882208fc5b3f5dff2cd473cc37765771a26fc4427a1916f4734616
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea609c0043193010729cd871249293e6c8a786e15681b5e59b3ffa03e5cc1df
+oid sha256:eee2afdaa2162f2d044e34766eb0070f6e0924f33e046ecd8efb0a8ab691c78d
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3dcd9ca70c393549b1be96b855d25c528e4d6ae0f537d236492acc5e80bc06
+oid sha256:0b89003a5e0fcaa0f5dfa9ec67ed1b82d48dd42cd4ad795734786e5193c88275
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbdf5cce354397b1cc7dbc75ae72cd1ce74fbf84991f656a8ae8c5ec4cf6c4c
+oid sha256:c91934808157be4b4581cbac88c1dcb8ab73e7092f7b8aa05c4fbac8ab77615f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07706837929731772,
+  "epoch": 0.08991310918020401,
   "eval_steps": 17,
-  "global_step": 102,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,49 @@
       "eval_samples_per_second": 36.078,
       "eval_steps_per_second": 4.514,
       "step": 102
+    },
+    {
+      "epoch": 0.07933509633547413,
+      "grad_norm": 0.04813135042786598,
+      "learning_rate": 5e-05,
+      "loss": 12.4455,
+      "step": 105
+    },
+    {
+      "epoch": 0.08160181337363052,
+      "grad_norm": 0.046277038753032684,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 12.4466,
+      "step": 108
+    },
+    {
+      "epoch": 0.08386853041178693,
+      "grad_norm": 0.046285875141620636,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 12.4448,
+      "step": 111
+    },
+    {
+      "epoch": 0.08613524744994333,
+      "grad_norm": 0.051637545228004456,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 12.4436,
+      "step": 114
+    },
+    {
+      "epoch": 0.08840196448809974,
+      "grad_norm": 0.04436314478516579,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 12.4446,
+      "step": 117
+    },
+    {
+      "epoch": 0.08991310918020401,
+      "eval_loss": 12.444755554199219,
+      "eval_runtime": 61.8074,
+      "eval_samples_per_second": 36.08,
+      "eval_steps_per_second": 4.514,
+      "step": 119
     }
   ],
   "logging_steps": 3,
@@ -320,7 +363,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225661943808.0,
+  "total_flos": 263272267776.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null