Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92680a30530f9b647cce84b014edc620a4402e12bae4c0110cf8fd3060796ec
+oid sha256:5339a81371d6b0f30eb16838dd6ae101c0d01993896d96018cd0ea162ff54d37
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6638f4ec6d804a5b2c99b69a8978721c820f3045f1cdcf4451ba40946bd764b6
+oid sha256:629ceaa6fe2a21b3f4b7adf949d73d82d85d25d8b6a1ee775aa8b8365bbbadb8
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefbaf2237cc7e49715dc76adf0218ac3527880444446bcd9b09f0856cf2828d
+oid sha256:6dd9219f72450659491ddb2f2e8718b04859a5b0ef31774019ad9ce07d518b69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003413202266366305,
+  "epoch": 0.00682640453273261,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 3.96,
       "eval_steps_per_second": 1.98,
       "step": 25
+    },
+    {
+      "epoch": 0.003549730357020957,
+      "grad_norm": 0.49614232778549194,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.6381,
+      "step": 26
+    },
+    {
+      "epoch": 0.0036862584476756092,
+      "grad_norm": 0.5684612393379211,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9167,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038227865383302613,
+      "grad_norm": 0.570894181728363,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.6912,
+      "step": 28
+    },
+    {
+      "epoch": 0.003959314628984914,
+      "grad_norm": 0.6302149891853333,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.9591,
+      "step": 29
+    },
+    {
+      "epoch": 0.0040958427196395655,
+      "grad_norm": 0.5717801451683044,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.0068,
+      "step": 30
+    },
+    {
+      "epoch": 0.004232370810294218,
+      "grad_norm": 0.5612018704414368,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.8452,
+      "step": 31
+    },
+    {
+      "epoch": 0.004368898900948871,
+      "grad_norm": 0.541138231754303,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.8667,
+      "step": 32
+    },
+    {
+      "epoch": 0.004505426991603522,
+      "grad_norm": 0.5489628911018372,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.0346,
+      "step": 33
+    },
+    {
+      "epoch": 0.004641955082258175,
+      "grad_norm": 0.5842531323432922,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.9291,
+      "step": 34
+    },
+    {
+      "epoch": 0.0047784831729128265,
+      "grad_norm": 0.6061104536056519,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.865,
+      "step": 35
+    },
+    {
+      "epoch": 0.004915011263567479,
+      "grad_norm": 0.7348506450653076,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.1669,
+      "step": 36
+    },
+    {
+      "epoch": 0.0050515393542221315,
+      "grad_norm": 0.6549107432365417,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.0044,
+      "step": 37
+    },
+    {
+      "epoch": 0.005188067444876783,
+      "grad_norm": 0.7873079180717468,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.3365,
+      "step": 38
+    },
+    {
+      "epoch": 0.005324595535531436,
+      "grad_norm": 0.7615660429000854,
+      "learning_rate": 5e-05,
+      "loss": 1.0544,
+      "step": 39
+    },
+    {
+      "epoch": 0.005461123626186087,
+      "grad_norm": 0.7403668761253357,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.3346,
+      "step": 40
+    },
+    {
+      "epoch": 0.00559765171684074,
+      "grad_norm": 0.8201382160186768,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.5327,
+      "step": 41
+    },
+    {
+      "epoch": 0.0057341798074953924,
+      "grad_norm": 0.7819324731826782,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3272,
+      "step": 42
+    },
+    {
+      "epoch": 0.005870707898150044,
+      "grad_norm": 0.7774024605751038,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.053,
+      "step": 43
+    },
+    {
+      "epoch": 0.006007235988804697,
+      "grad_norm": 0.9322003126144409,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.537,
+      "step": 44
+    },
+    {
+      "epoch": 0.006143764079459349,
+      "grad_norm": 1.4005628824234009,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.321,
+      "step": 45
+    },
+    {
+      "epoch": 0.006280292170114001,
+      "grad_norm": 1.4076716899871826,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.2719,
+      "step": 46
+    },
+    {
+      "epoch": 0.006416820260768653,
+      "grad_norm": 1.5207526683807373,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.2306,
+      "step": 47
+    },
+    {
+      "epoch": 0.006553348351423305,
+      "grad_norm": 1.6128692626953125,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3488,
+      "step": 48
+    },
+    {
+      "epoch": 0.0066898764420779576,
+      "grad_norm": 2.8725900650024414,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.7378,
+      "step": 49
+    },
+    {
+      "epoch": 0.00682640453273261,
+      "grad_norm": 8.908088684082031,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 3.1638,
+      "step": 50
+    },
+    {
+      "epoch": 0.00682640453273261,
+      "eval_loss": 1.095054030418396,
+      "eval_runtime": 1558.7732,
+      "eval_samples_per_second": 3.957,
+      "eval_steps_per_second": 1.978,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.748702522127155e+16,
+  "total_flos": 7.478754782950195e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null