Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f6f13109dd3fd2693bcc34ca6cf256e5f741bd656689207941dfd77819882e
+oid sha256:2e8cf1af962040beb8aeee5cef71beae48bb4668341815307d79336a5c9b352a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083e8bf04f6415840bd43e9f332eac39dbef9810ebede6b87288c9f5a7b69430
+oid sha256:e1c2943c6b5e79f01c2ae66c6b4cdac8be818848d89f3c0a0d770b06c89b48df
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbf52846b0950d1b0204ef5064ad518cb02596007e36540f5b060f1237792f0
+oid sha256:e5e6d6df32af28965e521ce09e49489f0f73a73e437d8780fef6228a2797f791
 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": 0.0032025278619923995,
+  "epoch": 0.004270037149323199,
   "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": 0.1916,
       "step": 75
+    },
+    {
+      "epoch": 0.003245228233485631,
+      "grad_norm": 0.35412412881851196,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1878,
+      "step": 76
+    },
+    {
+      "epoch": 0.0032879286049788633,
+      "grad_norm": 0.30525103211402893,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1653,
+      "step": 77
+    },
+    {
+      "epoch": 0.0033306289764720954,
+      "grad_norm": 0.39213159680366516,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2591,
+      "step": 78
+    },
+    {
+      "epoch": 0.003373329347965327,
+      "grad_norm": 0.3606932461261749,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2121,
+      "step": 79
+    },
+    {
+      "epoch": 0.0034160297194585592,
+      "grad_norm": 0.3313511908054352,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.191,
+      "step": 80
+    },
+    {
+      "epoch": 0.0034587300909517914,
+      "grad_norm": 0.3328807055950165,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2106,
+      "step": 81
+    },
+    {
+      "epoch": 0.0034587300909517914,
+      "eval_loss": 0.21893253922462463,
+      "eval_runtime": 1042.9691,
+      "eval_samples_per_second": 18.909,
+      "eval_steps_per_second": 2.364,
+      "step": 81
+    },
+    {
+      "epoch": 0.003501430462445023,
+      "grad_norm": 0.2882632315158844,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2033,
+      "step": 82
+    },
+    {
+      "epoch": 0.003544130833938255,
+      "grad_norm": 0.29635459184646606,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1779,
+      "step": 83
+    },
+    {
+      "epoch": 0.0035868312054314873,
+      "grad_norm": 0.33490076661109924,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2321,
+      "step": 84
+    },
+    {
+      "epoch": 0.0036295315769247194,
+      "grad_norm": 0.35736796259880066,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2227,
+      "step": 85
+    },
+    {
+      "epoch": 0.003672231948417951,
+      "grad_norm": 0.27138444781303406,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1776,
+      "step": 86
+    },
+    {
+      "epoch": 0.0037149323199111833,
+      "grad_norm": 0.3137736916542053,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2174,
+      "step": 87
+    },
+    {
+      "epoch": 0.0037576326914044154,
+      "grad_norm": 0.3758503496646881,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2291,
+      "step": 88
+    },
+    {
+      "epoch": 0.003800333062897647,
+      "grad_norm": 0.31046900153160095,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2707,
+      "step": 89
+    },
+    {
+      "epoch": 0.003843033434390879,
+      "grad_norm": 0.40348750352859497,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2896,
+      "step": 90
+    },
+    {
+      "epoch": 0.003843033434390879,
+      "eval_loss": 0.2182931900024414,
+      "eval_runtime": 1042.6209,
+      "eval_samples_per_second": 18.916,
+      "eval_steps_per_second": 2.365,
+      "step": 90
+    },
+    {
+      "epoch": 0.0038857338058841113,
+      "grad_norm": 0.3493230938911438,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2649,
+      "step": 91
+    },
+    {
+      "epoch": 0.0039284341773773435,
+      "grad_norm": 0.4098386764526367,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2941,
+      "step": 92
+    },
+    {
+      "epoch": 0.003971134548870575,
+      "grad_norm": 0.37344005703926086,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2413,
+      "step": 93
+    },
+    {
+      "epoch": 0.004013834920363807,
+      "grad_norm": 0.32273340225219727,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2232,
+      "step": 94
+    },
+    {
+      "epoch": 0.004056535291857039,
+      "grad_norm": 0.36059901118278503,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2346,
+      "step": 95
+    },
+    {
+      "epoch": 0.004099235663350271,
+      "grad_norm": 0.37520527839660645,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2152,
+      "step": 96
+    },
+    {
+      "epoch": 0.004141936034843503,
+      "grad_norm": 0.30212971568107605,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1743,
+      "step": 97
+    },
+    {
+      "epoch": 0.004184636406336735,
+      "grad_norm": 0.37452566623687744,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2375,
+      "step": 98
+    },
+    {
+      "epoch": 0.004227336777829967,
+      "grad_norm": 0.314308762550354,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1714,
+      "step": 99
+    },
+    {
+      "epoch": 0.004227336777829967,
+      "eval_loss": 0.21816055476665497,
+      "eval_runtime": 1042.752,
+      "eval_samples_per_second": 18.913,
+      "eval_steps_per_second": 2.365,
+      "step": 99
+    },
+    {
+      "epoch": 0.004270037149323199,
+      "grad_norm": 0.3065028786659241,
+      "learning_rate": 0.0,
+      "loss": 0.2229,
+      "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": 7.455967199782502e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null