Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cfe5ed253326636ede1ba97f5b0b93618f659831083ffc3c769280e8969d645
+oid sha256:094a11f26ef5197922b691e37bbf9794130cc7151f5dd23a0d9b6f833f9e6dfa
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56775d698fb2783416f108ba153efe22206e0afc17b5cdde67a702e9714fff58
+oid sha256:5c660f22b829a6ee30e3061ea102cfaef9634f5a190c29a8d71d9a6d2f6548fe
 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": 0.008675534991324466,
+  "epoch": 0.01156737998843262,
   "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": 1.0517,
       "step": 75
+    },
+    {
+      "epoch": 0.008791208791208791,
+      "grad_norm": 0.7473317980766296,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4491,
+      "step": 76
+    },
+    {
+      "epoch": 0.008906882591093117,
+      "grad_norm": 0.5357276797294617,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4757,
+      "step": 77
+    },
+    {
+      "epoch": 0.009022556390977444,
+      "grad_norm": 0.6168134212493896,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2008,
+      "step": 78
+    },
+    {
+      "epoch": 0.00913823019086177,
+      "grad_norm": 0.44112443923950195,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.2055,
+      "step": 79
+    },
+    {
+      "epoch": 0.009253903990746095,
+      "grad_norm": 0.8096681833267212,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4336,
+      "step": 80
+    },
+    {
+      "epoch": 0.009369577790630423,
+      "grad_norm": 0.645187258720398,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4662,
+      "step": 81
+    },
+    {
+      "epoch": 0.009369577790630423,
+      "eval_loss": 1.2884397506713867,
+      "eval_runtime": 740.1668,
+      "eval_samples_per_second": 9.836,
+      "eval_steps_per_second": 1.229,
+      "step": 81
+    },
+    {
+      "epoch": 0.009485251590514748,
+      "grad_norm": 0.5497397184371948,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3035,
+      "step": 82
+    },
+    {
+      "epoch": 0.009600925390399074,
+      "grad_norm": 0.6364536285400391,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3105,
+      "step": 83
+    },
+    {
+      "epoch": 0.009716599190283401,
+      "grad_norm": 0.5434615015983582,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.637,
+      "step": 84
+    },
+    {
+      "epoch": 0.009832272990167727,
+      "grad_norm": 0.4715433716773987,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2279,
+      "step": 85
+    },
+    {
+      "epoch": 0.009947946790052052,
+      "grad_norm": 0.5800156593322754,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3831,
+      "step": 86
+    },
+    {
+      "epoch": 0.01006362058993638,
+      "grad_norm": 0.6520781517028809,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.2524,
+      "step": 87
+    },
+    {
+      "epoch": 0.010179294389820705,
+      "grad_norm": 0.5186251997947693,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1758,
+      "step": 88
+    },
+    {
+      "epoch": 0.010294968189705031,
+      "grad_norm": 0.5043338537216187,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4261,
+      "step": 89
+    },
+    {
+      "epoch": 0.010410641989589358,
+      "grad_norm": 0.6483629941940308,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2404,
+      "step": 90
+    },
+    {
+      "epoch": 0.010410641989589358,
+      "eval_loss": 1.2871201038360596,
+      "eval_runtime": 739.8525,
+      "eval_samples_per_second": 9.84,
+      "eval_steps_per_second": 1.23,
+      "step": 90
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 0.5623393654823303,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2984,
+      "step": 91
+    },
+    {
+      "epoch": 0.01064198958935801,
+      "grad_norm": 0.49533864855766296,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3793,
+      "step": 92
+    },
+    {
+      "epoch": 0.010757663389242337,
+      "grad_norm": 0.6281312108039856,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.2025,
+      "step": 93
+    },
+    {
+      "epoch": 0.010873337189126663,
+      "grad_norm": 0.5476338267326355,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.338,
+      "step": 94
+    },
+    {
+      "epoch": 0.01098901098901099,
+      "grad_norm": 0.6564503312110901,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.283,
+      "step": 95
+    },
+    {
+      "epoch": 0.011104684788895315,
+      "grad_norm": 0.6445186138153076,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4782,
+      "step": 96
+    },
+    {
+      "epoch": 0.011220358588779641,
+      "grad_norm": 0.6720985174179077,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.194,
+      "step": 97
+    },
+    {
+      "epoch": 0.011336032388663968,
+      "grad_norm": 0.6252644062042236,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1304,
+      "step": 98
+    },
+    {
+      "epoch": 0.011451706188548294,
+      "grad_norm": 0.5523411631584167,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3266,
+      "step": 99
+    },
+    {
+      "epoch": 0.011451706188548294,
+      "eval_loss": 1.286765217781067,
+      "eval_runtime": 739.8084,
+      "eval_samples_per_second": 9.84,
+      "eval_steps_per_second": 1.23,
+      "step": 99
+    },
+    {
+      "epoch": 0.01156737998843262,
+      "grad_norm": 0.42987060546875,
+      "learning_rate": 0.0,
+      "loss": 1.151,
+      "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": 4.9582058766336e+16,
+  "total_flos": 6.6109411688448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null