Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4bd137bdb30bdaec19de6458144a5bfb31dd75f68e6396939f3fb20f117c9c
+oid sha256:a245d20f4ac02c71b8ce24288db018ed6160ff8c20543c0d037a208e16a174d3
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b982a15632a9f32c26624e0f75afb5778e6cb5503bd17524540feeb2a76ea1
+oid sha256:4765d3614659d4502291e321f65b8f4d401ef70fbc758de8faae1564bafc5476
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08550662676357418,
+  "epoch": 0.12825994014536127,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 107.276,
       "eval_steps_per_second": 53.747,
       "step": 50
+    },
+    {
+      "epoch": 0.08721675929884566,
+      "grad_norm": 0.4610964059829712,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.6814,
+      "step": 51
+    },
+    {
+      "epoch": 0.08892689183411714,
+      "grad_norm": 0.5062606930732727,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 11.6945,
+      "step": 52
+    },
+    {
+      "epoch": 0.09063702436938863,
+      "grad_norm": 0.553134560585022,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 11.6966,
+      "step": 53
+    },
+    {
+      "epoch": 0.09234715690466011,
+      "grad_norm": 0.5532500743865967,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 11.6781,
+      "step": 54
+    },
+    {
+      "epoch": 0.0940572894399316,
+      "grad_norm": 0.4720168113708496,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 11.7091,
+      "step": 55
+    },
+    {
+      "epoch": 0.09576742197520308,
+      "grad_norm": 0.5194851160049438,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 11.6756,
+      "step": 56
+    },
+    {
+      "epoch": 0.09747755451047456,
+      "grad_norm": 0.5085152387619019,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 11.6755,
+      "step": 57
+    },
+    {
+      "epoch": 0.09918768704574604,
+      "grad_norm": 0.5678163766860962,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 11.6762,
+      "step": 58
+    },
+    {
+      "epoch": 0.10089781958101753,
+      "grad_norm": 0.5167517066001892,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 11.663,
+      "step": 59
+    },
+    {
+      "epoch": 0.10260795211628901,
+      "grad_norm": 0.4949297606945038,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 11.6847,
+      "step": 60
+    },
+    {
+      "epoch": 0.10431808465156049,
+      "grad_norm": 0.5668756365776062,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 11.7024,
+      "step": 61
+    },
+    {
+      "epoch": 0.10602821718683197,
+      "grad_norm": 0.4657188355922699,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 11.6674,
+      "step": 62
+    },
+    {
+      "epoch": 0.10773834972210346,
+      "grad_norm": 0.5483532547950745,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 11.7355,
+      "step": 63
+    },
+    {
+      "epoch": 0.10944848225737494,
+      "grad_norm": 0.49865320324897766,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 11.6913,
+      "step": 64
+    },
+    {
+      "epoch": 0.11115861479264642,
+      "grad_norm": 0.4193071126937866,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 11.6589,
+      "step": 65
+    },
+    {
+      "epoch": 0.11286874732791792,
+      "grad_norm": 0.4931492209434509,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 11.684,
+      "step": 66
+    },
+    {
+      "epoch": 0.1145788798631894,
+      "grad_norm": 0.6170268058776855,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 11.678,
+      "step": 67
+    },
+    {
+      "epoch": 0.11628901239846089,
+      "grad_norm": 0.6914024353027344,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 11.6887,
+      "step": 68
+    },
+    {
+      "epoch": 0.11799914493373237,
+      "grad_norm": 0.538939356803894,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 11.7033,
+      "step": 69
+    },
+    {
+      "epoch": 0.11970927746900385,
+      "grad_norm": 0.5526518225669861,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 11.6602,
+      "step": 70
+    },
+    {
+      "epoch": 0.12141941000427534,
+      "grad_norm": 0.4771535396575928,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 11.6992,
+      "step": 71
+    },
+    {
+      "epoch": 0.12312954253954682,
+      "grad_norm": 0.5311975479125977,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 11.6501,
+      "step": 72
+    },
+    {
+      "epoch": 0.1248396750748183,
+      "grad_norm": 0.6137779951095581,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 11.6742,
+      "step": 73
+    },
+    {
+      "epoch": 0.12654980761008977,
+      "grad_norm": 0.4921776056289673,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 11.679,
+      "step": 74
+    },
+    {
+      "epoch": 0.12825994014536127,
+      "grad_norm": 0.4617028832435608,
+      "learning_rate": 0.0,
+      "loss": 11.6971,
+      "step": 75
+    },
+    {
+      "epoch": 0.12825994014536127,
+      "eval_loss": 11.677390098571777,
+      "eval_runtime": 4.5987,
+      "eval_samples_per_second": 107.204,
+      "eval_steps_per_second": 53.711,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 20370004377600.0,
+  "total_flos": 30555006566400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null