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:abee9defa2f4343dad896a46c39f88dc5e2d2b650491c0c4e7d2178312355299
+oid sha256:654d984e34734272ec7a818966144d6d6535beb5b714abff1c72319e45234726
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e158809030e00ab57a06e7f58d9209551ec0bf02f8cf1e23626ea2cae56c82d
+oid sha256:2887218cb09900466a9452eeecbeecb61780000b1fbe69f04d5253771c916ac6
 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": 0.7949807047843933,
-  "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 6.521739130434782,
+  "best_metric": 0.7308415770530701,
+  "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": 24.338,
       "eval_steps_per_second": 24.338,
       "step": 150
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 1.533442497253418,
+      "learning_rate": 2.9999892980750297e-05,
+      "loss": 0.6585,
+      "step": 160
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 1.3458119630813599,
+      "learning_rate": 2.9999854334972675e-05,
+      "loss": 0.7387,
+      "step": 170
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 1.726345419883728,
+      "learning_rate": 2.999980974373204e-05,
+      "loss": 0.729,
+      "step": 180
+    },
+    {
+      "epoch": 8.26086956521739,
+      "grad_norm": 1.540044903755188,
+      "learning_rate": 2.9999759207046075e-05,
+      "loss": 0.6246,
+      "step": 190
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.7418792247772217,
+      "learning_rate": 2.9999702724934804e-05,
+      "loss": 0.6761,
+      "step": 200
+    },
+    {
+      "epoch": 9.130434782608695,
+      "grad_norm": 1.038259506225586,
+      "learning_rate": 2.999964029742062e-05,
+      "loss": 0.6525,
+      "step": 210
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 1.2199773788452148,
+      "learning_rate": 2.9999571924528263e-05,
+      "loss": 0.5592,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5277819633483887,
+      "learning_rate": 2.9999497606284837e-05,
+      "loss": 0.7559,
+      "step": 230
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 1.4215247631072998,
+      "learning_rate": 2.9999417342719796e-05,
+      "loss": 0.7117,
+      "step": 240
+    },
+    {
+      "epoch": 10.869565217391305,
+      "grad_norm": 0.974700927734375,
+      "learning_rate": 2.9999331133864956e-05,
+      "loss": 0.5895,
+      "step": 250
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 1.1944469213485718,
+      "learning_rate": 2.9999238979754485e-05,
+      "loss": 0.6546,
+      "step": 260
+    },
+    {
+      "epoch": 11.73913043478261,
+      "grad_norm": 1.049609661102295,
+      "learning_rate": 2.999914088042492e-05,
+      "loss": 0.6475,
+      "step": 270
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 1.3114821910858154,
+      "learning_rate": 2.9999036835915132e-05,
+      "loss": 0.5939,
+      "step": 280
+    },
+    {
+      "epoch": 12.608695652173914,
+      "grad_norm": 1.0786523818969727,
+      "learning_rate": 2.9998926846266365e-05,
+      "loss": 0.633,
+      "step": 290
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 1.3863022327423096,
+      "learning_rate": 2.9998810911522213e-05,
+      "loss": 0.5808,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7308415770530701,
+      "eval_runtime": 0.5396,
+      "eval_samples_per_second": 18.534,
+      "eval_steps_per_second": 18.534,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.8609212040901184,
+      "eval_runtime": 0.5562,
+      "eval_samples_per_second": 17.98,
+      "eval_steps_per_second": 17.98,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7308415770530701,
+      "eval_runtime": 0.4963,
+      "eval_samples_per_second": 20.15,
+      "eval_steps_per_second": 20.15,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7747370004653931,
+      "eval_runtime": 0.5127,
+      "eval_samples_per_second": 19.506,
+      "eval_steps_per_second": 19.506,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.8607426881790161,
+      "eval_runtime": 0.5332,
+      "eval_samples_per_second": 18.756,
+      "eval_steps_per_second": 18.756,
+      "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