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:ea3f7c42361593b9f8f737265d6b2865fdd5bd91cf2532204e79dae8b9d9b3f6
+oid sha256:1279c05b0c1a6750151a97fd3b7d2a9ef1f0ac7aa94d7ea8d8663be38897e6ff
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f55f192214cc7fcc6706fb16e41bcff9288b8063e8a3df791f51f110c173f7d
+oid sha256:07dc5beb3c7b590e9fd599caaf3b65f90336f4a399489ea001faaabdd080a56d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb641ed1c277039af8b8ba2d9d53cbbb8c158dbe992dc8c6e1ce8826e06e00b0
+oid sha256:17917bbbb57276591a226a85ea518396eb01a0200369b98ab651385e568363c9
 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": 0.007471235742391792,
+  "epoch": 0.009961647656522389,
   "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": 1.3535,
       "step": 75
+    },
+    {
+      "epoch": 0.007570852218957015,
+      "grad_norm": 0.8664092421531677,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4339,
+      "step": 76
+    },
+    {
+      "epoch": 0.007670468695522239,
+      "grad_norm": 0.794583261013031,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.5005,
+      "step": 77
+    },
+    {
+      "epoch": 0.0077700851720874636,
+      "grad_norm": 0.6714551448822021,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3048,
+      "step": 78
+    },
+    {
+      "epoch": 0.007869701648652687,
+      "grad_norm": 0.7981712222099304,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4734,
+      "step": 79
+    },
+    {
+      "epoch": 0.00796931812521791,
+      "grad_norm": 0.8687072396278381,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8168,
+      "step": 80
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "grad_norm": 0.8038095831871033,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.6298,
+      "step": 81
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "eval_loss": 0.7665637731552124,
+      "eval_runtime": 1791.3829,
+      "eval_samples_per_second": 4.719,
+      "eval_steps_per_second": 0.59,
+      "step": 81
+    },
+    {
+      "epoch": 0.008168551078348359,
+      "grad_norm": 0.6158639788627625,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2939,
+      "step": 82
+    },
+    {
+      "epoch": 0.008268167554913582,
+      "grad_norm": 0.6034613847732544,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3772,
+      "step": 83
+    },
+    {
+      "epoch": 0.008367784031478807,
+      "grad_norm": 0.6227165460586548,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3024,
+      "step": 84
+    },
+    {
+      "epoch": 0.00846740050804403,
+      "grad_norm": 0.7155154347419739,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4845,
+      "step": 85
+    },
+    {
+      "epoch": 0.008567016984609254,
+      "grad_norm": 0.7330078482627869,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4502,
+      "step": 86
+    },
+    {
+      "epoch": 0.008666633461174479,
+      "grad_norm": 0.6891200542449951,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5192,
+      "step": 87
+    },
+    {
+      "epoch": 0.008766249937739702,
+      "grad_norm": 0.7983207702636719,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6114,
+      "step": 88
+    },
+    {
+      "epoch": 0.008865866414304925,
+      "grad_norm": 0.7906274795532227,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.6496,
+      "step": 89
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "grad_norm": 0.6719912886619568,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3213,
+      "step": 90
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "eval_loss": 0.7659702897071838,
+      "eval_runtime": 1791.5576,
+      "eval_samples_per_second": 4.719,
+      "eval_steps_per_second": 0.59,
+      "step": 90
+    },
+    {
+      "epoch": 0.009065099367435374,
+      "grad_norm": 0.7697194814682007,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6372,
+      "step": 91
+    },
+    {
+      "epoch": 0.009164715844000597,
+      "grad_norm": 0.6751009225845337,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.318,
+      "step": 92
+    },
+    {
+      "epoch": 0.009264332320565822,
+      "grad_norm": 0.6714102625846863,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.297,
+      "step": 93
+    },
+    {
+      "epoch": 0.009363948797131046,
+      "grad_norm": 0.8002302050590515,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6453,
+      "step": 94
+    },
+    {
+      "epoch": 0.009463565273696269,
+      "grad_norm": 0.6762931942939758,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5121,
+      "step": 95
+    },
+    {
+      "epoch": 0.009563181750261494,
+      "grad_norm": 0.7909438610076904,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3313,
+      "step": 96
+    },
+    {
+      "epoch": 0.009662798226826717,
+      "grad_norm": 0.6866534352302551,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.543,
+      "step": 97
+    },
+    {
+      "epoch": 0.00976241470339194,
+      "grad_norm": 0.6734254360198975,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4738,
+      "step": 98
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "grad_norm": 0.6834343671798706,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4935,
+      "step": 99
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "eval_loss": 0.7658064365386963,
+      "eval_runtime": 1791.8569,
+      "eval_samples_per_second": 4.718,
+      "eval_steps_per_second": 0.59,
+      "step": 99
+    },
+    {
+      "epoch": 0.009961647656522389,
+      "grad_norm": 0.6811820864677429,
+      "learning_rate": 0.0,
+      "loss": 1.5149,
+      "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": 9.648701542760448e+16,
+  "total_flos": 1.2886094823555072e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null