Training in progress, step 393, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553199fdc2537d7b05a0adc14757ccd53736eb16e0503423d60ffc788cb7233e
+oid sha256:3de684adefc361bb1d4d11889a5540b73e550a6ccbb59cda58c56985ab531360
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c5a2f7c0c45286f6c522767b85fceec31d05bd276498c9e4b2d066e5d8ce87
+oid sha256:3d417abc1e45f0525c5982ac26a620f7ee3bc80b16e5e34519eff524ee3a0786
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a667add586611e44a4c54951a74a518d746ca5cc9dcf7bff18f64ea62134064
+oid sha256:6419ed2e05cb2dcb7b39272409bc22caaac7a923df5ec9f68043073806f6ecfa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2cfbb94a7008a15fd5a6375b1221914718ea48bfd979d64e56e5e2ef78603d3
+oid sha256:0759b211eaa5cabac925cd5a8e9d5634a1e8903d4118da279ffe887612eb9731
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7709923664122136,
+  "epoch": 3.0,
   "eval_steps": 33,
-  "global_step": 363,
+  "global_step": 393,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -950,6 +950,76 @@
       "eval_samples_per_second": 23.823,
       "eval_steps_per_second": 6.037,
       "step": 363
+    },
+    {
+      "epoch": 2.7938931297709924,
+      "grad_norm": 0.5983389019966125,
+      "learning_rate": 1.2212198858607694e-06,
+      "loss": 0.0637,
+      "step": 366
+    },
+    {
+      "epoch": 2.816793893129771,
+      "grad_norm": 0.2721739113330841,
+      "learning_rate": 9.657431935277627e-07,
+      "loss": 0.0363,
+      "step": 369
+    },
+    {
+      "epoch": 2.8396946564885495,
+      "grad_norm": 0.15959583222866058,
+      "learning_rate": 7.399573346368871e-07,
+      "loss": 0.0463,
+      "step": 372
+    },
+    {
+      "epoch": 2.8625954198473282,
+      "grad_norm": 0.20066188275814056,
+      "learning_rate": 5.439990252467886e-07,
+      "loss": 0.0341,
+      "step": 375
+    },
+    {
+      "epoch": 2.885496183206107,
+      "grad_norm": 0.13702194392681122,
+      "learning_rate": 3.779869204754427e-07,
+      "loss": 0.026,
+      "step": 378
+    },
+    {
+      "epoch": 2.9083969465648853,
+      "grad_norm": 0.22333796322345734,
+      "learning_rate": 2.420215426530259e-07,
+      "loss": 0.0755,
+      "step": 381
+    },
+    {
+      "epoch": 2.931297709923664,
+      "grad_norm": 0.8999789953231812,
+      "learning_rate": 1.3618522045439895e-07,
+      "loss": 0.0687,
+      "step": 384
+    },
+    {
+      "epoch": 2.954198473282443,
+      "grad_norm": 0.200925812125206,
+      "learning_rate": 6.054203904817812e-08,
+      "loss": 0.0491,
+      "step": 387
+    },
+    {
+      "epoch": 2.9770992366412212,
+      "grad_norm": 0.5747220516204834,
+      "learning_rate": 1.5137801292325336e-08,
+      "loss": 0.0822,
+      "step": 390
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.17193453013896942,
+      "learning_rate": 0.0,
+      "loss": 0.0331,
+      "step": 393
     }
   ],
   "logging_steps": 3,
@@ -964,12 +1034,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7374807349303706e+17,
+  "total_flos": 2.96352206649557e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null