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:c5756efdd3f2b9c0541ef4e4d0207e159ba53672260a9f7bb35d211b2b163fb2
+oid sha256:35de6aa7dde713affbad57ebbf259fa16226c0c1a897456151126b3d13a07da1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64156bb8074d8dcc615b811856512bcccfda9d295483948506c269649abea99b
+oid sha256:9cb4513beed50d264b5b224d3f247b1e11e5f292ff99c3b36d458802c3b571c6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.3393665158371041,
+  "epoch": 0.45248868778280543,
   "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": 1.6301,
       "step": 75
+    },
+    {
+      "epoch": 0.3438914027149321,
+      "grad_norm": 0.565269410610199,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6623,
+      "step": 76
+    },
+    {
+      "epoch": 0.34841628959276016,
+      "grad_norm": 0.6384878754615784,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.8242,
+      "step": 77
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.5925453305244446,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.747,
+      "step": 78
+    },
+    {
+      "epoch": 0.3574660633484163,
+      "grad_norm": 0.6376003623008728,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.8284,
+      "step": 79
+    },
+    {
+      "epoch": 0.36199095022624433,
+      "grad_norm": 0.7476432919502258,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0615,
+      "step": 80
+    },
+    {
+      "epoch": 0.3665158371040724,
+      "grad_norm": 0.6390846371650696,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.7909,
+      "step": 81
+    },
+    {
+      "epoch": 0.3665158371040724,
+      "eval_loss": 1.9013618230819702,
+      "eval_runtime": 20.4953,
+      "eval_samples_per_second": 9.075,
+      "eval_steps_per_second": 1.171,
+      "step": 81
+    },
+    {
+      "epoch": 0.37104072398190047,
+      "grad_norm": 0.6754607558250427,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6204,
+      "step": 82
+    },
+    {
+      "epoch": 0.3755656108597285,
+      "grad_norm": 0.6686813831329346,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.977,
+      "step": 83
+    },
+    {
+      "epoch": 0.38009049773755654,
+      "grad_norm": 0.5270020365715027,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7243,
+      "step": 84
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.6310787200927734,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4172,
+      "step": 85
+    },
+    {
+      "epoch": 0.3891402714932127,
+      "grad_norm": 0.5818957090377808,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.6233,
+      "step": 86
+    },
+    {
+      "epoch": 0.3936651583710407,
+      "grad_norm": 0.5629267692565918,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5551,
+      "step": 87
+    },
+    {
+      "epoch": 0.39819004524886875,
+      "grad_norm": 0.5803009867668152,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7285,
+      "step": 88
+    },
+    {
+      "epoch": 0.40271493212669685,
+      "grad_norm": 0.6951214075088501,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.0041,
+      "step": 89
+    },
+    {
+      "epoch": 0.4072398190045249,
+      "grad_norm": 0.56612628698349,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6706,
+      "step": 90
+    },
+    {
+      "epoch": 0.4072398190045249,
+      "eval_loss": 1.900350570678711,
+      "eval_runtime": 20.4948,
+      "eval_samples_per_second": 9.075,
+      "eval_steps_per_second": 1.171,
+      "step": 90
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.6141659617424011,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.8772,
+      "step": 91
+    },
+    {
+      "epoch": 0.416289592760181,
+      "grad_norm": 0.5659681558609009,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.6687,
+      "step": 92
+    },
+    {
+      "epoch": 0.42081447963800905,
+      "grad_norm": 0.6701894402503967,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.746,
+      "step": 93
+    },
+    {
+      "epoch": 0.4253393665158371,
+      "grad_norm": 0.5552034974098206,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6563,
+      "step": 94
+    },
+    {
+      "epoch": 0.4298642533936652,
+      "grad_norm": 0.7257485389709473,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.714,
+      "step": 95
+    },
+    {
+      "epoch": 0.4343891402714932,
+      "grad_norm": 0.7610495686531067,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.9043,
+      "step": 96
+    },
+    {
+      "epoch": 0.43891402714932126,
+      "grad_norm": 0.5871830582618713,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.9222,
+      "step": 97
+    },
+    {
+      "epoch": 0.4434389140271493,
+      "grad_norm": 0.580263078212738,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6688,
+      "step": 98
+    },
+    {
+      "epoch": 0.4479638009049774,
+      "grad_norm": 0.7358007431030273,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.7251,
+      "step": 99
+    },
+    {
+      "epoch": 0.4479638009049774,
+      "eval_loss": 1.8997759819030762,
+      "eval_runtime": 20.4943,
+      "eval_samples_per_second": 9.076,
+      "eval_steps_per_second": 1.171,
+      "step": 99
+    },
+    {
+      "epoch": 0.45248868778280543,
+      "grad_norm": 0.594517171382904,
+      "learning_rate": 0.0,
+      "loss": 1.4599,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null