Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b1f51030bb007cb8c00cb787e59a0fcb3c57367f52fa71ff12f385654f08f5
+oid sha256:7db897091c403983d5b73a85d76a376de57da2de2b0164b135b9f73457ca9266
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db25879075003f326cc6d3b89c659737a69de1b88d39d171ff9237e3d44d3fd
+oid sha256:e244b84c58e98ccdab7fdf65ea43314d196298f5e689bbc64f991c1466162c3f
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
+oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14749262536873156,
+  "epoch": 0.22123893805309736,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 2.5148,
       "step": 50
+    },
+    {
+      "epoch": 0.1504424778761062,
+      "grad_norm": 1.5208971500396729,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.0899,
+      "step": 51
+    },
+    {
+      "epoch": 0.15339233038348082,
+      "grad_norm": 3.4418222904205322,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.4397,
+      "step": 52
+    },
+    {
+      "epoch": 0.15634218289085547,
+      "grad_norm": 2.2392663955688477,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.8609,
+      "step": 53
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "grad_norm": 2.139505386352539,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.0997,
+      "step": 54
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "eval_loss": 0.9444321990013123,
+      "eval_runtime": 44.3343,
+      "eval_samples_per_second": 6.451,
+      "eval_steps_per_second": 0.812,
+      "step": 54
+    },
+    {
+      "epoch": 0.16224188790560473,
+      "grad_norm": 2.0930261611938477,
+      "learning_rate": 5e-05,
+      "loss": 1.7881,
+      "step": 55
+    },
+    {
+      "epoch": 0.16519174041297935,
+      "grad_norm": 2.2204813957214355,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.7174,
+      "step": 56
+    },
+    {
+      "epoch": 0.168141592920354,
+      "grad_norm": 2.269932746887207,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.685,
+      "step": 57
+    },
+    {
+      "epoch": 0.1710914454277286,
+      "grad_norm": 2.4379570484161377,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3988,
+      "step": 58
+    },
+    {
+      "epoch": 0.17404129793510326,
+      "grad_norm": 2.7614104747772217,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.7063,
+      "step": 59
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 3.342813491821289,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0876,
+      "step": 60
+    },
+    {
+      "epoch": 0.17994100294985252,
+      "grad_norm": 1.874851107597351,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.41,
+      "step": 61
+    },
+    {
+      "epoch": 0.18289085545722714,
+      "grad_norm": 2.886047124862671,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7038,
+      "step": 62
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "grad_norm": 2.56038498878479,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.9275,
+      "step": 63
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "eval_loss": 0.9344019293785095,
+      "eval_runtime": 44.3805,
+      "eval_samples_per_second": 6.444,
+      "eval_steps_per_second": 0.811,
+      "step": 63
+    },
+    {
+      "epoch": 0.1887905604719764,
+      "grad_norm": 2.8928627967834473,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.076,
+      "step": 64
+    },
+    {
+      "epoch": 0.19174041297935104,
+      "grad_norm": 2.5595240592956543,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.8227,
+      "step": 65
+    },
+    {
+      "epoch": 0.19469026548672566,
+      "grad_norm": 2.3376636505126953,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.8931,
+      "step": 66
+    },
+    {
+      "epoch": 0.1976401179941003,
+      "grad_norm": 1.9027594327926636,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.4452,
+      "step": 67
+    },
+    {
+      "epoch": 0.20058997050147492,
+      "grad_norm": 2.5550875663757324,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9689,
+      "step": 68
+    },
+    {
+      "epoch": 0.20353982300884957,
+      "grad_norm": 2.062281608581543,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.372,
+      "step": 69
+    },
+    {
+      "epoch": 0.20648967551622419,
+      "grad_norm": 2.665297508239746,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7928,
+      "step": 70
+    },
+    {
+      "epoch": 0.20943952802359883,
+      "grad_norm": 2.0745885372161865,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.4635,
+      "step": 71
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "grad_norm": 2.8449113368988037,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.0457,
+      "step": 72
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "eval_loss": 0.9305321574211121,
+      "eval_runtime": 44.3666,
+      "eval_samples_per_second": 6.446,
+      "eval_steps_per_second": 0.811,
+      "step": 72
+    },
+    {
+      "epoch": 0.2153392330383481,
+      "grad_norm": 2.6109533309936523,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7443,
+      "step": 73
+    },
+    {
+      "epoch": 0.2182890855457227,
+      "grad_norm": 2.955402135848999,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8344,
+      "step": 74
+    },
+    {
+      "epoch": 0.22123893805309736,
+      "grad_norm": 3.2939834594726562,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.3507,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 9.521684545536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null