Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d751659c276aef20f64ac2086bb94283b0199bd1f1e60569293bb547eb39b0
+oid sha256:b41b2828a6719d2653880e9164ae4fc661a8d76abad7b0061be6b920fa28bce0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baea272a437adecddff11c50a301dfe72269a0ce587fb8d212644a5b778f39b4
+oid sha256:eac0d8224d123cce2ef6f5dadf17d1fc156faa104f8c646a9887842e5764b1ff
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b161438ec76da89999600124f2b412e50aee4c6eea9f51d76090346c14b7c9ff
+oid sha256:175434b22fa8805eb7958ee3c6fa1d076bbb21655f587c1f0790cc944a1f8c55
 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": 0.008306337735692334,
+  "epoch": 0.012459506603538499,
   "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": 1.7434,
       "step": 50
+    },
+    {
+      "epoch": 0.00847246449040618,
+      "grad_norm": 1.392175555229187,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.627,
+      "step": 51
+    },
+    {
+      "epoch": 0.008638591245120026,
+      "grad_norm": 2.5748090744018555,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.297,
+      "step": 52
+    },
+    {
+      "epoch": 0.008804717999833874,
+      "grad_norm": 1.3663445711135864,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.9941,
+      "step": 53
+    },
+    {
+      "epoch": 0.00897084475454772,
+      "grad_norm": 1.5222846269607544,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8739,
+      "step": 54
+    },
+    {
+      "epoch": 0.00897084475454772,
+      "eval_loss": 0.6527463793754578,
+      "eval_runtime": 675.2164,
+      "eval_samples_per_second": 7.507,
+      "eval_steps_per_second": 0.939,
+      "step": 54
+    },
+    {
+      "epoch": 0.009136971509261566,
+      "grad_norm": 1.4149327278137207,
+      "learning_rate": 5e-05,
+      "loss": 1.0193,
+      "step": 55
+    },
+    {
+      "epoch": 0.009303098263975414,
+      "grad_norm": 1.3249423503875732,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.386,
+      "step": 56
+    },
+    {
+      "epoch": 0.00946922501868926,
+      "grad_norm": 1.4684275388717651,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.6665,
+      "step": 57
+    },
+    {
+      "epoch": 0.009635351773403106,
+      "grad_norm": 0.864578902721405,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.6305,
+      "step": 58
+    },
+    {
+      "epoch": 0.009801478528116954,
+      "grad_norm": 0.8630561828613281,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.5473,
+      "step": 59
+    },
+    {
+      "epoch": 0.0099676052828308,
+      "grad_norm": 1.2544828653335571,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.0987,
+      "step": 60
+    },
+    {
+      "epoch": 0.010133732037544647,
+      "grad_norm": 1.6959971189498901,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.9921,
+      "step": 61
+    },
+    {
+      "epoch": 0.010299858792258493,
+      "grad_norm": 1.5748471021652222,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.033,
+      "step": 62
+    },
+    {
+      "epoch": 0.01046598554697234,
+      "grad_norm": 0.922096312046051,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.8486,
+      "step": 63
+    },
+    {
+      "epoch": 0.01046598554697234,
+      "eval_loss": 0.6467626094818115,
+      "eval_runtime": 675.6424,
+      "eval_samples_per_second": 7.502,
+      "eval_steps_per_second": 0.938,
+      "step": 63
+    },
+    {
+      "epoch": 0.010632112301686187,
+      "grad_norm": 1.0161826610565186,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.1515,
+      "step": 64
+    },
+    {
+      "epoch": 0.010798239056400033,
+      "grad_norm": 0.8706979751586914,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.8809,
+      "step": 65
+    },
+    {
+      "epoch": 0.01096436581111388,
+      "grad_norm": 1.361327052116394,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.8019,
+      "step": 66
+    },
+    {
+      "epoch": 0.011130492565827727,
+      "grad_norm": 0.8916012048721313,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.9665,
+      "step": 67
+    },
+    {
+      "epoch": 0.011296619320541573,
+      "grad_norm": 1.261985182762146,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.5859,
+      "step": 68
+    },
+    {
+      "epoch": 0.01146274607525542,
+      "grad_norm": 1.4368607997894287,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.3238,
+      "step": 69
+    },
+    {
+      "epoch": 0.011628872829969267,
+      "grad_norm": 3.813182830810547,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1585,
+      "step": 70
+    },
+    {
+      "epoch": 0.011794999584683113,
+      "grad_norm": 1.8414254188537598,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.3511,
+      "step": 71
+    },
+    {
+      "epoch": 0.01196112633939696,
+      "grad_norm": 2.074822187423706,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1272,
+      "step": 72
+    },
+    {
+      "epoch": 0.01196112633939696,
+      "eval_loss": 0.6417830586433411,
+      "eval_runtime": 675.5888,
+      "eval_samples_per_second": 7.503,
+      "eval_steps_per_second": 0.938,
+      "step": 72
+    },
+    {
+      "epoch": 0.012127253094110807,
+      "grad_norm": 1.6472017765045166,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.2974,
+      "step": 73
+    },
+    {
+      "epoch": 0.012293379848824653,
+      "grad_norm": 0.7575200200080872,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0512,
+      "step": 74
+    },
+    {
+      "epoch": 0.012459506603538499,
+      "grad_norm": 0.760666012763977,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.3661,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.868263604178125e+16,
+  "total_flos": 7.155367310838989e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null