Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a96603bd8eee4cf918c9772a26520b8760099bd8f4cd2de014624bf4fa4c7f
+oid sha256:2c571c3d9bc97035512218123eb16c4a5ac39adeb400b8f87dca66f9daff0f4c
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4fd2108d49d07e4d7bee6998e7ecb19e375ff49d05de755c3a44b4b5c6c6dc5
+oid sha256:4bb2b5192e62889a659f5c32729030ddd962b6ab8d9ab4f6e8f06e1b2f7f86d0
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5feb56512e955691dc9bb9a1e37b9dd590e06a961d7d94560b679e2730b03194
+oid sha256:037d13720220086c05f76f1146cd4356e8b9d075b5d306338df00d366045e1c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
+oid sha256:6f4c00d522bdde510099aafe1617b13d114dce17a17b44e05876f016f4e4d7af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7962104678153992,
-  "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 6.521739130434782,
+  "best_metric": 0.7310147881507874,
+  "best_model_checkpoint": "./output/checkpoint-300",
+  "epoch": 13.043478260869565,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,151 @@
       "eval_samples_per_second": 25.287,
       "eval_steps_per_second": 25.287,
       "step": 150
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 1.540989637374878,
+      "learning_rate": 2.9999892980750297e-05,
+      "loss": 0.6586,
+      "step": 160
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 1.345400094985962,
+      "learning_rate": 2.9999854334972675e-05,
+      "loss": 0.739,
+      "step": 170
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 1.725967526435852,
+      "learning_rate": 2.999980974373204e-05,
+      "loss": 0.7291,
+      "step": 180
+    },
+    {
+      "epoch": 8.26086956521739,
+      "grad_norm": 1.5401579141616821,
+      "learning_rate": 2.9999759207046075e-05,
+      "loss": 0.6245,
+      "step": 190
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.7425003051757812,
+      "learning_rate": 2.9999702724934804e-05,
+      "loss": 0.6765,
+      "step": 200
+    },
+    {
+      "epoch": 9.130434782608695,
+      "grad_norm": 1.0419254302978516,
+      "learning_rate": 2.999964029742062e-05,
+      "loss": 0.6524,
+      "step": 210
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 1.2119251489639282,
+      "learning_rate": 2.9999571924528263e-05,
+      "loss": 0.5593,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5276358127593994,
+      "learning_rate": 2.9999497606284837e-05,
+      "loss": 0.756,
+      "step": 230
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 1.413993000984192,
+      "learning_rate": 2.9999417342719796e-05,
+      "loss": 0.7116,
+      "step": 240
+    },
+    {
+      "epoch": 10.869565217391305,
+      "grad_norm": 0.9750322699546814,
+      "learning_rate": 2.9999331133864956e-05,
+      "loss": 0.5897,
+      "step": 250
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 1.1936322450637817,
+      "learning_rate": 2.9999238979754485e-05,
+      "loss": 0.6547,
+      "step": 260
+    },
+    {
+      "epoch": 11.73913043478261,
+      "grad_norm": 1.0489903688430786,
+      "learning_rate": 2.999914088042492e-05,
+      "loss": 0.6475,
+      "step": 270
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 1.3138858079910278,
+      "learning_rate": 2.9999036835915132e-05,
+      "loss": 0.5937,
+      "step": 280
+    },
+    {
+      "epoch": 12.608695652173914,
+      "grad_norm": 1.0842424631118774,
+      "learning_rate": 2.9998926846266365e-05,
+      "loss": 0.6326,
+      "step": 290
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 1.3883247375488281,
+      "learning_rate": 2.9998810911522213e-05,
+      "loss": 0.5806,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7310147881507874,
+      "eval_runtime": 0.4443,
+      "eval_samples_per_second": 22.51,
+      "eval_steps_per_second": 22.51,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.8606523275375366,
+      "eval_runtime": 0.4404,
+      "eval_samples_per_second": 22.708,
+      "eval_steps_per_second": 22.708,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7310147881507874,
+      "eval_runtime": 0.4391,
+      "eval_samples_per_second": 22.773,
+      "eval_steps_per_second": 22.773,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7758375406265259,
+      "eval_runtime": 0.4396,
+      "eval_samples_per_second": 22.75,
+      "eval_steps_per_second": 22.75,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.860957145690918,
+      "eval_runtime": 0.4444,
+      "eval_samples_per_second": 22.5,
+      "eval_steps_per_second": 22.5,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -171,7 +316,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3894839614291968.0,
+  "total_flos": 7724643094462464.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null