Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e056a6c824bd2b82bcfb4b22fd4c452b5e6e252f473644e6707d9e7aa905426
+oid sha256:6b2b60e76b14fdabeef97b4cf899c3d70bc9023731b0fb156cfb0e294721bec2
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382ca0bf57a11f5a5578b3cf7085b8d51e0355e4bc3b3550cdc1bd3403ebd59c
+oid sha256:f1d0624c5e8cd1547c17438f7a3af3b48df3ebbb5d9f65b94dd29c88511acbe8
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfcaaae51171e7f2154bf7987e0cee9b37d43cdaad7e0a601e845794e2d16a7a
+oid sha256:3363d5b297615a86bf49f3cc89fc13a41d8a4cccce26fdc41518c47e65d9e887
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980f3048c9e624e61f36d02f7920ce9a18fb66e5656e6f4264f835f0c860998f
+oid sha256:6fdc9ddea5f8e3dd4316c80a90ac4dccf5346af4de901f2eaefea337178ab218
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18364ede1da3fcfa616bf4b04a3b725bd669a65c375cfdd782448d68f791d203
+oid sha256:ac6db595ac08860028e5d3a0421a258d62e79b9181595e1db7b1d6301bce70f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184c568fce2131695bfc392333c69a45c01f3b8659492da73b71968597bb3421
+oid sha256:6bf42ea7e5acd83b8d7a6b9460832eaf0d889e951c9a76571af8ee6f4ec7f16d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
+oid sha256:4bd95a1db0e917ddf11b12a343f06e907fcec4b81104002e2471b4778587b465
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4389288047028086,
+  "epoch": 0.5486610058785107,
   "eval_steps": 42,
-  "global_step": 168,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -439,6 +439,112 @@
       "eval_samples_per_second": 776.625,
       "eval_steps_per_second": 24.401,
       "step": 168
+    },
+    {
+      "epoch": 0.44676681907250165,
+      "grad_norm": 0.019369367510080338,
+      "learning_rate": 7.564496387029532e-05,
+      "loss": 11.9192,
+      "step": 171
+    },
+    {
+      "epoch": 0.45460483344219466,
+      "grad_norm": 0.012970932759344578,
+      "learning_rate": 7.481469062821252e-05,
+      "loss": 11.9188,
+      "step": 174
+    },
+    {
+      "epoch": 0.46244284781188766,
+      "grad_norm": 0.012391473166644573,
+      "learning_rate": 7.39752373250527e-05,
+      "loss": 11.919,
+      "step": 177
+    },
+    {
+      "epoch": 0.47028086218158066,
+      "grad_norm": 0.014110087417066097,
+      "learning_rate": 7.312691451204178e-05,
+      "loss": 11.9184,
+      "step": 180
+    },
+    {
+      "epoch": 0.47811887655127366,
+      "grad_norm": 0.016782281920313835,
+      "learning_rate": 7.227003602163295e-05,
+      "loss": 11.9177,
+      "step": 183
+    },
+    {
+      "epoch": 0.48595689092096667,
+      "grad_norm": 0.013867055997252464,
+      "learning_rate": 7.14049188514063e-05,
+      "loss": 11.9188,
+      "step": 186
+    },
+    {
+      "epoch": 0.4937949052906597,
+      "grad_norm": 0.022281071171164513,
+      "learning_rate": 7.05318830467969e-05,
+      "loss": 11.9179,
+      "step": 189
+    },
+    {
+      "epoch": 0.5016329196603527,
+      "grad_norm": 0.014964847825467587,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 11.9187,
+      "step": 192
+    },
+    {
+      "epoch": 0.5094709340300457,
+      "grad_norm": 0.012438995763659477,
+      "learning_rate": 6.876335024396872e-05,
+      "loss": 11.9191,
+      "step": 195
+    },
+    {
+      "epoch": 0.5173089483997387,
+      "grad_norm": 0.016654090955853462,
+      "learning_rate": 6.786850750493006e-05,
+      "loss": 11.918,
+      "step": 198
+    },
+    {
+      "epoch": 0.5251469627694317,
+      "grad_norm": 0.019343817606568336,
+      "learning_rate": 6.696705440782938e-05,
+      "loss": 11.9178,
+      "step": 201
+    },
+    {
+      "epoch": 0.5329849771391247,
+      "grad_norm": 0.017074916511774063,
+      "learning_rate": 6.605932444038229e-05,
+      "loss": 11.9185,
+      "step": 204
+    },
+    {
+      "epoch": 0.5408229915088177,
+      "grad_norm": 0.016646448522806168,
+      "learning_rate": 6.514565341239861e-05,
+      "loss": 11.918,
+      "step": 207
+    },
+    {
+      "epoch": 0.5486610058785107,
+      "grad_norm": 0.013506593182682991,
+      "learning_rate": 6.422637933155162e-05,
+      "loss": 11.9185,
+      "step": 210
+    },
+    {
+      "epoch": 0.5486610058785107,
+      "eval_loss": 11.917922019958496,
+      "eval_runtime": 3.3182,
+      "eval_samples_per_second": 776.922,
+      "eval_steps_per_second": 24.411,
+      "step": 210
     }
   ],
   "logging_steps": 3,
@@ -458,7 +564,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3240801730560.0,
+  "total_flos": 4050700861440.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null