Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc6727bbb5908ece0c0ecb1fbd9a5a096a1aa52586834f7494bfdded29479f2
+oid sha256:903d54125756f147e6d12665a1fe5d9199a7ffd8015de5082c70ff4c51833e05
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d21be4d1da4660651205e701227296b7339e8919e04276d283aa971add7983
+oid sha256:a16d6206a22dfe7d235ea6aa9af3004145ee55719ea7b70cfd7bc0eea6d3ebf9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4934210526315789,
+  "epoch": 0.6578947368421053,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 3.1575,
       "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.1724132299423218,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.919,
+      "step": 76
+    },
+    {
+      "epoch": 0.506578947368421,
+      "grad_norm": 1.2114452123641968,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.6806,
+      "step": 77
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 1.2915575504302979,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.6593,
+      "step": 78
+    },
+    {
+      "epoch": 0.5197368421052632,
+      "grad_norm": 1.0405056476593018,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.988,
+      "step": 79
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.0308349132537842,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.5931,
+      "step": 80
+    },
+    {
+      "epoch": 0.5328947368421053,
+      "grad_norm": 1.2563862800598145,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.2365,
+      "step": 81
+    },
+    {
+      "epoch": 0.5328947368421053,
+      "eval_loss": 1.3557542562484741,
+      "eval_runtime": 11.8127,
+      "eval_samples_per_second": 10.92,
+      "eval_steps_per_second": 1.439,
+      "step": 81
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 1.1508125066757202,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.4557,
+      "step": 82
+    },
+    {
+      "epoch": 0.5460526315789473,
+      "grad_norm": 1.2678468227386475,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.6471,
+      "step": 83
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 1.2328356504440308,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.8384,
+      "step": 84
+    },
+    {
+      "epoch": 0.5592105263157895,
+      "grad_norm": 1.3108208179473877,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.5576,
+      "step": 85
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 1.195551872253418,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.7296,
+      "step": 86
+    },
+    {
+      "epoch": 0.5723684210526315,
+      "grad_norm": 1.2313472032546997,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.6876,
+      "step": 87
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 1.1951091289520264,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7786,
+      "step": 88
+    },
+    {
+      "epoch": 0.5855263157894737,
+      "grad_norm": 1.2675416469573975,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.7165,
+      "step": 89
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 1.135334849357605,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.7501,
+      "step": 90
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "eval_loss": 1.355621337890625,
+      "eval_runtime": 11.818,
+      "eval_samples_per_second": 10.916,
+      "eval_steps_per_second": 1.438,
+      "step": 90
+    },
+    {
+      "epoch": 0.5986842105263158,
+      "grad_norm": 1.2185972929000854,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.348,
+      "step": 91
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 1.2187449932098389,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.9864,
+      "step": 92
+    },
+    {
+      "epoch": 0.6118421052631579,
+      "grad_norm": 1.176838755607605,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.9543,
+      "step": 93
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 1.1729670763015747,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.7812,
+      "step": 94
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.0939475297927856,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.7562,
+      "step": 95
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1.284177541732788,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.7301,
+      "step": 96
+    },
+    {
+      "epoch": 0.6381578947368421,
+      "grad_norm": 1.2222950458526611,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.3219,
+      "step": 97
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 1.2235487699508667,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.538,
+      "step": 98
+    },
+    {
+      "epoch": 0.6513157894736842,
+      "grad_norm": 1.1274579763412476,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.5219,
+      "step": 99
+    },
+    {
+      "epoch": 0.6513157894736842,
+      "eval_loss": 1.3554550409317017,
+      "eval_runtime": 11.828,
+      "eval_samples_per_second": 10.906,
+      "eval_steps_per_second": 1.437,
+      "step": 99
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 1.147770643234253,
+      "learning_rate": 0.0,
+      "loss": 2.2666,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.90093651427328e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null