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:a99ea3fdd078c3802dcdb8eb557864a51de709c43dfee49ee7215e36457e279a
+oid sha256:1c3139078b35610e0b65fee3953cb1c0f07431a75b481287a93d39240d78d107
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3d83d747e9ffdad1de3aa3c3e6a2cafee874565cd784e7fcf585eb0e2f2bf6
+oid sha256:f1bd2c097d8151a4a1e9e6256043754fc7149f35124d11d731bdd0b01a7e014f
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.26455026455026454,
+  "epoch": 0.3527336860670194,
   "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": 0.1775,
       "step": 75
+    },
+    {
+      "epoch": 0.26807760141093473,
+      "grad_norm": 2.312260389328003,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2314,
+      "step": 76
+    },
+    {
+      "epoch": 0.2716049382716049,
+      "grad_norm": 5.711832523345947,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6443,
+      "step": 77
+    },
+    {
+      "epoch": 0.2751322751322751,
+      "grad_norm": 1.8561723232269287,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0904,
+      "step": 78
+    },
+    {
+      "epoch": 0.2786596119929453,
+      "grad_norm": 4.764100551605225,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4073,
+      "step": 79
+    },
+    {
+      "epoch": 0.2821869488536155,
+      "grad_norm": 7.698202610015869,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8285,
+      "step": 80
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 3.3542370796203613,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.3216,
+      "step": 81
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_loss": 0.1273738294839859,
+      "eval_runtime": 37.6563,
+      "eval_samples_per_second": 6.347,
+      "eval_steps_per_second": 0.797,
+      "step": 81
+    },
+    {
+      "epoch": 0.2892416225749559,
+      "grad_norm": 1.7140568494796753,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2145,
+      "step": 82
+    },
+    {
+      "epoch": 0.2927689594356261,
+      "grad_norm": 5.036262512207031,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2936,
+      "step": 83
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 3.415752649307251,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2426,
+      "step": 84
+    },
+    {
+      "epoch": 0.2998236331569665,
+      "grad_norm": 4.9717535972595215,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3977,
+      "step": 85
+    },
+    {
+      "epoch": 0.30335097001763667,
+      "grad_norm": 4.338818073272705,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2631,
+      "step": 86
+    },
+    {
+      "epoch": 0.30687830687830686,
+      "grad_norm": 2.277334690093994,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2695,
+      "step": 87
+    },
+    {
+      "epoch": 0.31040564373897706,
+      "grad_norm": 3.494274139404297,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2478,
+      "step": 88
+    },
+    {
+      "epoch": 0.31393298059964725,
+      "grad_norm": 2.0326128005981445,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1626,
+      "step": 89
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 2.125136375427246,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3441,
+      "step": 90
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "eval_loss": 0.09313661605119705,
+      "eval_runtime": 37.6783,
+      "eval_samples_per_second": 6.343,
+      "eval_steps_per_second": 0.796,
+      "step": 90
+    },
+    {
+      "epoch": 0.32098765432098764,
+      "grad_norm": 0.8155926465988159,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.101,
+      "step": 91
+    },
+    {
+      "epoch": 0.32451499118165783,
+      "grad_norm": 1.1524417400360107,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0992,
+      "step": 92
+    },
+    {
+      "epoch": 0.328042328042328,
+      "grad_norm": 2.5966567993164062,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1509,
+      "step": 93
+    },
+    {
+      "epoch": 0.3315696649029982,
+      "grad_norm": 4.279085159301758,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3135,
+      "step": 94
+    },
+    {
+      "epoch": 0.3350970017636684,
+      "grad_norm": 2.5114855766296387,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2901,
+      "step": 95
+    },
+    {
+      "epoch": 0.3386243386243386,
+      "grad_norm": 3.0181519985198975,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2685,
+      "step": 96
+    },
+    {
+      "epoch": 0.3421516754850088,
+      "grad_norm": 2.5745158195495605,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1457,
+      "step": 97
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 3.473428726196289,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3729,
+      "step": 98
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 3.5403099060058594,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2323,
+      "step": 99
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "eval_loss": 0.0885021910071373,
+      "eval_runtime": 37.6512,
+      "eval_samples_per_second": 6.348,
+      "eval_steps_per_second": 0.797,
+      "step": 99
+    },
+    {
+      "epoch": 0.3527336860670194,
+      "grad_norm": 4.210207462310791,
+      "learning_rate": 0.0,
+      "loss": 0.2794,
+      "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": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null