Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d9cb540c5a860ee18428d97e9c6a2c9413c826ef861b10bfe2273b4ba87918
+oid sha256:f06a94a8fd2110630b29f1a0fd61ece5d491e081468de01dce6bcb49a29196b3
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb303aed8062be2e28e6c28799dc86de07c6cd39ee42a654f3ed5866ddcc7f5a
+oid sha256:583aa4e7918fb15bddf477cd5bcb1d9cae4199ecc8a16903e5bbd6fb6f6c04a5
 size 591203178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be6285b51eb8628843ebcf538440997e9983602416b820387811937bd0b2278
+oid sha256:822082b213c0642410a7baeaf5135c14aa4c940d0ddb23409fe69b75772aee28
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2369912416280269,
+  "epoch": 1.6491499227202473,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -476,6 +476,162 @@
       "eval_samples_per_second": 0.408,
       "eval_steps_per_second": 0.408,
       "step": 600
+    },
+    {
+      "epoch": 1.2575991756826377,
+      "grad_norm": 0.5280514359474182,
+      "learning_rate": 7.217943436218728e-05,
+      "loss": 0.1515,
+      "step": 610
+    },
+    {
+      "epoch": 1.2782071097372487,
+      "grad_norm": 0.5676441788673401,
+      "learning_rate": 7.109767620035689e-05,
+      "loss": 0.1345,
+      "step": 620
+    },
+    {
+      "epoch": 1.2988150437918597,
+      "grad_norm": 0.5746245980262756,
+      "learning_rate": 7.000376641716133e-05,
+      "loss": 0.1387,
+      "step": 630
+    },
+    {
+      "epoch": 1.3194229778464708,
+      "grad_norm": 0.6514201164245605,
+      "learning_rate": 6.889833507144532e-05,
+      "loss": 0.1185,
+      "step": 640
+    },
+    {
+      "epoch": 1.3400309119010818,
+      "grad_norm": 0.7305589318275452,
+      "learning_rate": 6.778201885812404e-05,
+      "loss": 0.1569,
+      "step": 650
+    },
+    {
+      "epoch": 1.3606388459556928,
+      "grad_norm": 0.41217121481895447,
+      "learning_rate": 6.66554607414661e-05,
+      "loss": 0.1469,
+      "step": 660
+    },
+    {
+      "epoch": 1.3812467800103039,
+      "grad_norm": 0.4568374454975128,
+      "learning_rate": 6.551930958476571e-05,
+      "loss": 0.1249,
+      "step": 670
+    },
+    {
+      "epoch": 1.401854714064915,
+      "grad_norm": 0.567737340927124,
+      "learning_rate": 6.437421977661709e-05,
+      "loss": 0.1348,
+      "step": 680
+    },
+    {
+      "epoch": 1.422462648119526,
+      "grad_norm": 0.5140897035598755,
+      "learning_rate": 6.322085085400644e-05,
+      "loss": 0.1274,
+      "step": 690
+    },
+    {
+      "epoch": 1.443070582174137,
+      "grad_norm": 0.6037400960922241,
+      "learning_rate": 6.205986712243875e-05,
+      "loss": 0.1437,
+      "step": 700
+    },
+    {
+      "epoch": 1.443070582174137,
+      "eval_loss": 0.1935451626777649,
+      "eval_runtime": 146.9127,
+      "eval_samples_per_second": 0.408,
+      "eval_steps_per_second": 0.408,
+      "step": 700
+    },
+    {
+      "epoch": 1.463678516228748,
+      "grad_norm": 0.5562382340431213,
+      "learning_rate": 6.0891937273317935e-05,
+      "loss": 0.1407,
+      "step": 710
+    },
+    {
+      "epoch": 1.484286450283359,
+      "grad_norm": 0.4450112581253052,
+      "learning_rate": 5.9717733998800803e-05,
+      "loss": 0.1474,
+      "step": 720
+    },
+    {
+      "epoch": 1.50489438433797,
+      "grad_norm": 0.5950725674629211,
+      "learning_rate": 5.853793360434687e-05,
+      "loss": 0.1393,
+      "step": 730
+    },
+    {
+      "epoch": 1.525502318392581,
+      "grad_norm": 0.5703924298286438,
+      "learning_rate": 5.735321561918697e-05,
+      "loss": 0.1396,
+      "step": 740
+    },
+    {
+      "epoch": 1.5461102524471921,
+      "grad_norm": 0.5534270405769348,
+      "learning_rate": 5.61642624049349e-05,
+      "loss": 0.1296,
+      "step": 750
+    },
+    {
+      "epoch": 1.5667181865018032,
+      "grad_norm": 0.5007007122039795,
+      "learning_rate": 5.497175876256796e-05,
+      "loss": 0.1261,
+      "step": 760
+    },
+    {
+      "epoch": 1.5873261205564142,
+      "grad_norm": 0.6271963715553284,
+      "learning_rate": 5.377639153800229e-05,
+      "loss": 0.1513,
+      "step": 770
+    },
+    {
+      "epoch": 1.6079340546110252,
+      "grad_norm": 0.5237583518028259,
+      "learning_rate": 5.2578849226490525e-05,
+      "loss": 0.1465,
+      "step": 780
+    },
+    {
+      "epoch": 1.6285419886656363,
+      "grad_norm": 0.4081502854824066,
+      "learning_rate": 5.137982157606937e-05,
+      "loss": 0.1214,
+      "step": 790
+    },
+    {
+      "epoch": 1.6491499227202473,
+      "grad_norm": 0.670275866985321,
+      "learning_rate": 5.017999919028566e-05,
+      "loss": 0.1371,
+      "step": 800
+    },
+    {
+      "epoch": 1.6491499227202473,
+      "eval_loss": 0.19273868203163147,
+      "eval_runtime": 146.7244,
+      "eval_samples_per_second": 0.409,
+      "eval_steps_per_second": 0.409,
+      "step": 800
     }
   ],
   "logging_steps": 10,
@@ -495,7 +651,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.221911898996736e+16,
+  "total_flos": 4.309328094007296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null