Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f77b4fd09d3f94efb73575982a12e150fee3cf2f1787df3d420c044d912eff
+oid sha256:1c19e79bfc7218471e2f02b8488b99570d8eb74541da314b866a722de1d25795
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d0ca45d28b1cdf658e975e19212aeed45a7128a3e1fd9d25fbef3033538a24
+oid sha256:947d2942a5f129077a90f200b9ea1ddd02e0bc612a825c5ae6a8f25039b440e4
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d44637ce5e861ad816fd68fdeece15df6bfd52efa4d86d6394515a6a4dcaa3
+oid sha256:83602fb516e190adb15f8e96cf9832025b7b49d10d73e9f5b4a29cc997ba0fe8
 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": 0.0019156843463046449,
+  "epoch": 0.0025542457950728597,
   "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": 1.7224,
       "step": 75
+    },
+    {
+      "epoch": 0.0019412268042553736,
+      "grad_norm": 0.7415811419487,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.7479,
+      "step": 76
+    },
+    {
+      "epoch": 0.001966769262206102,
+      "grad_norm": 0.7497789263725281,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6142,
+      "step": 77
+    },
+    {
+      "epoch": 0.0019923117201568305,
+      "grad_norm": 0.7450811266899109,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.6518,
+      "step": 78
+    },
+    {
+      "epoch": 0.0020178541781075594,
+      "grad_norm": 0.7852325439453125,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.7654,
+      "step": 79
+    },
+    {
+      "epoch": 0.002043396636058288,
+      "grad_norm": 0.8051366806030273,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7341,
+      "step": 80
+    },
+    {
+      "epoch": 0.0020689390940090164,
+      "grad_norm": 0.8135154843330383,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.8232,
+      "step": 81
+    },
+    {
+      "epoch": 0.0020689390940090164,
+      "eval_loss": 1.7158979177474976,
+      "eval_runtime": 3435.2389,
+      "eval_samples_per_second": 9.597,
+      "eval_steps_per_second": 1.2,
+      "step": 81
+    },
+    {
+      "epoch": 0.002094481551959745,
+      "grad_norm": 0.7492078542709351,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8427,
+      "step": 82
+    },
+    {
+      "epoch": 0.002120024009910474,
+      "grad_norm": 0.7200819253921509,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.5653,
+      "step": 83
+    },
+    {
+      "epoch": 0.0021455664678612023,
+      "grad_norm": 0.7568774223327637,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.683,
+      "step": 84
+    },
+    {
+      "epoch": 0.0021711089258119307,
+      "grad_norm": 0.725376307964325,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.7622,
+      "step": 85
+    },
+    {
+      "epoch": 0.0021966513837626597,
+      "grad_norm": 0.7259377241134644,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.67,
+      "step": 86
+    },
+    {
+      "epoch": 0.002222193841713388,
+      "grad_norm": 0.7849528193473816,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.6941,
+      "step": 87
+    },
+    {
+      "epoch": 0.0022477362996641166,
+      "grad_norm": 0.7939113974571228,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.698,
+      "step": 88
+    },
+    {
+      "epoch": 0.002273278757614845,
+      "grad_norm": 0.787257730960846,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.8319,
+      "step": 89
+    },
+    {
+      "epoch": 0.002298821215565574,
+      "grad_norm": 0.7407448887825012,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6219,
+      "step": 90
+    },
+    {
+      "epoch": 0.002298821215565574,
+      "eval_loss": 1.7123228311538696,
+      "eval_runtime": 3435.2036,
+      "eval_samples_per_second": 9.597,
+      "eval_steps_per_second": 1.2,
+      "step": 90
+    },
+    {
+      "epoch": 0.0023243636735163025,
+      "grad_norm": 0.7486845850944519,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.7262,
+      "step": 91
+    },
+    {
+      "epoch": 0.002349906131467031,
+      "grad_norm": 0.7758967280387878,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.6374,
+      "step": 92
+    },
+    {
+      "epoch": 0.00237544858941776,
+      "grad_norm": 0.7840884923934937,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6898,
+      "step": 93
+    },
+    {
+      "epoch": 0.0024009910473684884,
+      "grad_norm": 0.7477433681488037,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6497,
+      "step": 94
+    },
+    {
+      "epoch": 0.002426533505319217,
+      "grad_norm": 0.7921217083930969,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7386,
+      "step": 95
+    },
+    {
+      "epoch": 0.0024520759632699453,
+      "grad_norm": 0.760387659072876,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.824,
+      "step": 96
+    },
+    {
+      "epoch": 0.0024776184212206742,
+      "grad_norm": 0.7254878282546997,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.732,
+      "step": 97
+    },
+    {
+      "epoch": 0.0025031608791714027,
+      "grad_norm": 0.7777676582336426,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6284,
+      "step": 98
+    },
+    {
+      "epoch": 0.002528703337122131,
+      "grad_norm": 0.7612666487693787,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.7225,
+      "step": 99
+    },
+    {
+      "epoch": 0.002528703337122131,
+      "eval_loss": 1.711596131324768,
+      "eval_runtime": 3435.3717,
+      "eval_samples_per_second": 9.597,
+      "eval_steps_per_second": 1.2,
+      "step": 99
+    },
+    {
+      "epoch": 0.0025542457950728597,
+      "grad_norm": 0.7312284708023071,
+      "learning_rate": 0.0,
+      "loss": 1.6075,
+      "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": 2.4695190061056e+16,
+  "total_flos": 3.2926920081408e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null