Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d65670007d9d49d58ec8a8d224b9020089b5bc65d934c443aeb3eab1034e602
+oid sha256:51d56661225f3462247db1309fb13218a65c8e0321443673171be439dde9f235
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b54941fa59b691cf4b597e6ef4f9415f5531984fc72f74cd6a4e28cbf8e53a
+oid sha256:f779785d3f1995edf32e20fbe5bce7b751928ce0a6a71358a3fa576e0c9d3254
 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": 0.7009345794392523,
+  "epoch": 0.9345794392523364,
   "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": 0.2422,
       "step": 75
+    },
+    {
+      "epoch": 0.7102803738317757,
+      "grad_norm": 0.5746442079544067,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2505,
+      "step": 76
+    },
+    {
+      "epoch": 0.719626168224299,
+      "grad_norm": 0.8767488598823547,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.247,
+      "step": 77
+    },
+    {
+      "epoch": 0.7289719626168224,
+      "grad_norm": 0.7167015075683594,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2451,
+      "step": 78
+    },
+    {
+      "epoch": 0.7383177570093458,
+      "grad_norm": 1.2198740243911743,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2493,
+      "step": 79
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.6779648065567017,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2161,
+      "step": 80
+    },
+    {
+      "epoch": 0.7570093457943925,
+      "grad_norm": 0.7529325485229492,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2551,
+      "step": 81
+    },
+    {
+      "epoch": 0.7570093457943925,
+      "eval_loss": 0.12358495593070984,
+      "eval_runtime": 8.88,
+      "eval_samples_per_second": 10.135,
+      "eval_steps_per_second": 1.351,
+      "step": 81
+    },
+    {
+      "epoch": 0.7663551401869159,
+      "grad_norm": 0.740033745765686,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2112,
+      "step": 82
+    },
+    {
+      "epoch": 0.7757009345794392,
+      "grad_norm": 0.8699694275856018,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2286,
+      "step": 83
+    },
+    {
+      "epoch": 0.7850467289719626,
+      "grad_norm": 0.439491331577301,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.228,
+      "step": 84
+    },
+    {
+      "epoch": 0.794392523364486,
+      "grad_norm": 0.6666630506515503,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2204,
+      "step": 85
+    },
+    {
+      "epoch": 0.8037383177570093,
+      "grad_norm": 0.44219282269477844,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2274,
+      "step": 86
+    },
+    {
+      "epoch": 0.8130841121495327,
+      "grad_norm": 0.6741518974304199,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2334,
+      "step": 87
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": 0.5375016927719116,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2219,
+      "step": 88
+    },
+    {
+      "epoch": 0.8317757009345794,
+      "grad_norm": 0.5032656192779541,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2078,
+      "step": 89
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "grad_norm": 0.6404811143875122,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2303,
+      "step": 90
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "eval_loss": 0.12498477101325989,
+      "eval_runtime": 8.8908,
+      "eval_samples_per_second": 10.123,
+      "eval_steps_per_second": 1.35,
+      "step": 90
+    },
+    {
+      "epoch": 0.8504672897196262,
+      "grad_norm": 0.8548187613487244,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2475,
+      "step": 91
+    },
+    {
+      "epoch": 0.8598130841121495,
+      "grad_norm": 0.7053015828132629,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2288,
+      "step": 92
+    },
+    {
+      "epoch": 0.8691588785046729,
+      "grad_norm": 1.0452989339828491,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2491,
+      "step": 93
+    },
+    {
+      "epoch": 0.8785046728971962,
+      "grad_norm": 0.5804879069328308,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2201,
+      "step": 94
+    },
+    {
+      "epoch": 0.8878504672897196,
+      "grad_norm": 0.7856619954109192,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2481,
+      "step": 95
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 0.8506635427474976,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.239,
+      "step": 96
+    },
+    {
+      "epoch": 0.9065420560747663,
+      "grad_norm": 0.7877066731452942,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2645,
+      "step": 97
+    },
+    {
+      "epoch": 0.9158878504672897,
+      "grad_norm": 0.5927013158798218,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2305,
+      "step": 98
+    },
+    {
+      "epoch": 0.9252336448598131,
+      "grad_norm": 0.5697266459465027,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2202,
+      "step": 99
+    },
+    {
+      "epoch": 0.9252336448598131,
+      "eval_loss": 0.12411493808031082,
+      "eval_runtime": 8.8981,
+      "eval_samples_per_second": 10.114,
+      "eval_steps_per_second": 1.349,
+      "step": 99
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7628682255744934,
+      "learning_rate": 0.0,
+      "loss": 0.2392,
+      "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