Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f7bdf167759cae2f9b6f9fae05ea36727393d4272640e5019aa52225e4ca1d
+oid sha256:e728a0aad5d79ae5682e950c29f8089cab77c4ba26ff99cb6191b4e0d65e87c4
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2cb205489d162abcc1da8febf612044a8f89414d1df3c78d4167551ff72324e
+oid sha256:c5ac006d816c65c22fe85e003fc02374113ea7166d423284d61ec5f59517d59b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
+oid sha256:23b292c0efb28eea88c002c7c382d68ce9c4cd641c1f3fb777ab6b43a2d8a19d
 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": 0.025214321734745335,
+  "epoch": 0.03361909564632711,
   "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": 0.6978,
       "step": 75
+    },
+    {
+      "epoch": 0.025550512691208605,
+      "grad_norm": 0.1675630807876587,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7317,
+      "step": 76
+    },
+    {
+      "epoch": 0.02588670364767188,
+      "grad_norm": 0.1723320633172989,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.7211,
+      "step": 77
+    },
+    {
+      "epoch": 0.026222894604135148,
+      "grad_norm": 0.1641874462366104,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7723,
+      "step": 78
+    },
+    {
+      "epoch": 0.02655908556059842,
+      "grad_norm": 0.1716737598180771,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6314,
+      "step": 79
+    },
+    {
+      "epoch": 0.02689527651706169,
+      "grad_norm": 0.18608728051185608,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8172,
+      "step": 80
+    },
+    {
+      "epoch": 0.02723146747352496,
+      "grad_norm": 0.1537061631679535,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.647,
+      "step": 81
+    },
+    {
+      "epoch": 0.02723146747352496,
+      "eval_loss": 0.38487839698791504,
+      "eval_runtime": 520.5682,
+      "eval_samples_per_second": 4.812,
+      "eval_steps_per_second": 0.603,
+      "step": 81
+    },
+    {
+      "epoch": 0.027567658429988234,
+      "grad_norm": 0.16313450038433075,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7868,
+      "step": 82
+    },
+    {
+      "epoch": 0.027903849386451504,
+      "grad_norm": 0.1759936660528183,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.8788,
+      "step": 83
+    },
+    {
+      "epoch": 0.028240040342914774,
+      "grad_norm": 0.19584429264068604,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6019,
+      "step": 84
+    },
+    {
+      "epoch": 0.028576231299378047,
+      "grad_norm": 0.16350510716438293,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7671,
+      "step": 85
+    },
+    {
+      "epoch": 0.028912422255841317,
+      "grad_norm": 0.2040233165025711,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9043,
+      "step": 86
+    },
+    {
+      "epoch": 0.02924861321230459,
+      "grad_norm": 0.15660732984542847,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.6308,
+      "step": 87
+    },
+    {
+      "epoch": 0.02958480416876786,
+      "grad_norm": 0.1986546367406845,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.7612,
+      "step": 88
+    },
+    {
+      "epoch": 0.02992099512523113,
+      "grad_norm": 0.19693925976753235,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.8345,
+      "step": 89
+    },
+    {
+      "epoch": 0.030257186081694403,
+      "grad_norm": 0.18926070630550385,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8594,
+      "step": 90
+    },
+    {
+      "epoch": 0.030257186081694403,
+      "eval_loss": 0.3840206265449524,
+      "eval_runtime": 520.3941,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 0.603,
+      "step": 90
+    },
+    {
+      "epoch": 0.030593377038157673,
+      "grad_norm": 0.38893425464630127,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0024,
+      "step": 91
+    },
+    {
+      "epoch": 0.030929567994620946,
+      "grad_norm": 0.18008224666118622,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.7867,
+      "step": 92
+    },
+    {
+      "epoch": 0.031265758951084216,
+      "grad_norm": 0.19447776675224304,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.8256,
+      "step": 93
+    },
+    {
+      "epoch": 0.031601949907547486,
+      "grad_norm": 0.2075979858636856,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7926,
+      "step": 94
+    },
+    {
+      "epoch": 0.031938140864010756,
+      "grad_norm": 0.18590274453163147,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9474,
+      "step": 95
+    },
+    {
+      "epoch": 0.03227433182047403,
+      "grad_norm": 0.17288009822368622,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0012,
+      "step": 96
+    },
+    {
+      "epoch": 0.0326105227769373,
+      "grad_norm": 0.18136736750602722,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.8246,
+      "step": 97
+    },
+    {
+      "epoch": 0.03294671373340057,
+      "grad_norm": 0.14506976306438446,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.686,
+      "step": 98
+    },
+    {
+      "epoch": 0.03328290468986384,
+      "grad_norm": 0.1989787220954895,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6926,
+      "step": 99
+    },
+    {
+      "epoch": 0.03328290468986384,
+      "eval_loss": 0.3838490843772888,
+      "eval_runtime": 520.5769,
+      "eval_samples_per_second": 4.812,
+      "eval_steps_per_second": 0.603,
+      "step": 99
+    },
+    {
+      "epoch": 0.03361909564632711,
+      "grad_norm": 0.19118410348892212,
+      "learning_rate": 0.0,
+      "loss": 0.9295,
+      "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": 9.5217449435136e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null