Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a14e964e8b864305ea78a7fdeafb5078259c7f289105ca5d77633d942f52362
+oid sha256:576a8707d2f0cd3e94022107f6a50d9e652a924132062a112dbc8d2770ec0843
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9a70b54575abd23d9b4b2b09933073ae02d0d6c76cee2d518e36c614491ec8
+oid sha256:7a7f648de8edb6eb81f622342bcdcf635cf5f3efb325751867d933ad5718ef5f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82070ffe55ccbf8a10ae05c44e293986e51c38a62e2b8b84945035270d2adeb
+oid sha256:f66f2426252eb191beb77c78c058090472268dcbf13daa8cf60071225acfe904
 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": 0.0396746677246578,
+  "epoch": 0.05951200158698671,
   "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": 4.983,
       "eval_steps_per_second": 2.491,
       "step": 50
+    },
+    {
+      "epoch": 0.04046816107915096,
+      "grad_norm": 4.387226581573486,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.8696,
+      "step": 51
+    },
+    {
+      "epoch": 0.041261654433644115,
+      "grad_norm": 3.4610178470611572,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 2.9204,
+      "step": 52
+    },
+    {
+      "epoch": 0.04205514778813727,
+      "grad_norm": 3.9737682342529297,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 2.7895,
+      "step": 53
+    },
+    {
+      "epoch": 0.04284864114263043,
+      "grad_norm": 4.6396660804748535,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.74,
+      "step": 54
+    },
+    {
+      "epoch": 0.043642134497123584,
+      "grad_norm": 4.616176605224609,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 2.9485,
+      "step": 55
+    },
+    {
+      "epoch": 0.04443562785161674,
+      "grad_norm": 4.061956882476807,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 2.8803,
+      "step": 56
+    },
+    {
+      "epoch": 0.0452291212061099,
+      "grad_norm": 3.080620050430298,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.8301,
+      "step": 57
+    },
+    {
+      "epoch": 0.04602261456060305,
+      "grad_norm": 4.132306098937988,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 2.9382,
+      "step": 58
+    },
+    {
+      "epoch": 0.04681610791509621,
+      "grad_norm": 3.9911930561065674,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 2.6713,
+      "step": 59
+    },
+    {
+      "epoch": 0.047609601269589366,
+      "grad_norm": 4.608588695526123,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.0239,
+      "step": 60
+    },
+    {
+      "epoch": 0.04840309462408252,
+      "grad_norm": 4.470647811889648,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 2.7732,
+      "step": 61
+    },
+    {
+      "epoch": 0.04919658797857568,
+      "grad_norm": 2.497837543487549,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 2.7511,
+      "step": 62
+    },
+    {
+      "epoch": 0.049990081333068835,
+      "grad_norm": 3.23616361618042,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.9893,
+      "step": 63
+    },
+    {
+      "epoch": 0.05078357468756199,
+      "grad_norm": 3.335463762283325,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 2.8443,
+      "step": 64
+    },
+    {
+      "epoch": 0.05157706804205515,
+      "grad_norm": 5.495422840118408,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 2.7337,
+      "step": 65
+    },
+    {
+      "epoch": 0.052370561396548304,
+      "grad_norm": 4.613150119781494,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.2081,
+      "step": 66
+    },
+    {
+      "epoch": 0.05316405475104146,
+      "grad_norm": 4.699667930603027,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 3.0643,
+      "step": 67
+    },
+    {
+      "epoch": 0.05395754810553462,
+      "grad_norm": 49.308128356933594,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 3.1513,
+      "step": 68
+    },
+    {
+      "epoch": 0.05475104146002777,
+      "grad_norm": 2.868114948272705,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.7152,
+      "step": 69
+    },
+    {
+      "epoch": 0.05554453481452093,
+      "grad_norm": 3.7996325492858887,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 2.8909,
+      "step": 70
+    },
+    {
+      "epoch": 0.056338028169014086,
+      "grad_norm": 3.899604320526123,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.8813,
+      "step": 71
+    },
+    {
+      "epoch": 0.05713152152350724,
+      "grad_norm": 5.131252288818359,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.9879,
+      "step": 72
+    },
+    {
+      "epoch": 0.0579250148780004,
+      "grad_norm": 4.755951404571533,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 2.9316,
+      "step": 73
+    },
+    {
+      "epoch": 0.058718508232493555,
+      "grad_norm": 3.195016622543335,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 2.9473,
+      "step": 74
+    },
+    {
+      "epoch": 0.05951200158698671,
+      "grad_norm": 3.24080753326416,
+      "learning_rate": 0.0,
+      "loss": 3.016,
+      "step": 75
+    },
+    {
+      "epoch": 0.05951200158698671,
+      "eval_loss": 0.36618655920028687,
+      "eval_runtime": 214.2318,
+      "eval_samples_per_second": 4.957,
+      "eval_steps_per_second": 2.479,
+      "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": 6.53458201903104e+16,
+  "total_flos": 9.80187302854656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null