Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb3f79ebd113c7defb846e60886619f4e2018296b21028d12d194f50b8edb84
+oid sha256:d89ef3fb1a8c75c0dc08a6efc853c74a58e61fc0681127eb9e819aded96aa8ed
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dad4c885c578ce19c5069c1c0a00b827afe3b546f61f482b4b626271dbc5852
+oid sha256:0e399281e2e551cfc56d79bf5c5c718e10523406f9a34d49f5aaee41e438412e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
+oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
 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": 0.06199628022318661,
+  "epoch": 0.0929944203347799,
   "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": 0.3312,
       "step": 50
+    },
+    {
+      "epoch": 0.06323620582765034,
+      "grad_norm": 2.2069196701049805,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.1405,
+      "step": 51
+    },
+    {
+      "epoch": 0.06447613143211407,
+      "grad_norm": 3.5193231105804443,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2545,
+      "step": 52
+    },
+    {
+      "epoch": 0.0657160570365778,
+      "grad_norm": 3.9061081409454346,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.5383,
+      "step": 53
+    },
+    {
+      "epoch": 0.06695598264104154,
+      "grad_norm": 3.045947551727295,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2484,
+      "step": 54
+    },
+    {
+      "epoch": 0.06695598264104154,
+      "eval_loss": 0.3930973410606384,
+      "eval_runtime": 74.6298,
+      "eval_samples_per_second": 9.098,
+      "eval_steps_per_second": 1.139,
+      "step": 54
+    },
+    {
+      "epoch": 0.06819590824550527,
+      "grad_norm": 3.8757569789886475,
+      "learning_rate": 5e-05,
+      "loss": 0.6221,
+      "step": 55
+    },
+    {
+      "epoch": 0.069435833849969,
+      "grad_norm": 2.1376354694366455,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1202,
+      "step": 56
+    },
+    {
+      "epoch": 0.07067575945443273,
+      "grad_norm": 2.5388710498809814,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.3296,
+      "step": 57
+    },
+    {
+      "epoch": 0.07191568505889646,
+      "grad_norm": 2.990429639816284,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1526,
+      "step": 58
+    },
+    {
+      "epoch": 0.0731556106633602,
+      "grad_norm": 4.948442459106445,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.0436,
+      "step": 59
+    },
+    {
+      "epoch": 0.07439553626782393,
+      "grad_norm": 7.169388771057129,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8199,
+      "step": 60
+    },
+    {
+      "epoch": 0.07563546187228766,
+      "grad_norm": 3.115478277206421,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.2636,
+      "step": 61
+    },
+    {
+      "epoch": 0.07687538747675139,
+      "grad_norm": 3.5272696018218994,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5775,
+      "step": 62
+    },
+    {
+      "epoch": 0.07811531308121512,
+      "grad_norm": 3.178927183151245,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.3514,
+      "step": 63
+    },
+    {
+      "epoch": 0.07811531308121512,
+      "eval_loss": 0.37893226742744446,
+      "eval_runtime": 74.5475,
+      "eval_samples_per_second": 9.108,
+      "eval_steps_per_second": 1.14,
+      "step": 63
+    },
+    {
+      "epoch": 0.07935523868567886,
+      "grad_norm": 1.964901328086853,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1657,
+      "step": 64
+    },
+    {
+      "epoch": 0.08059516429014259,
+      "grad_norm": 4.481605052947998,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.8851,
+      "step": 65
+    },
+    {
+      "epoch": 0.08183508989460632,
+      "grad_norm": 1.225839376449585,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0641,
+      "step": 66
+    },
+    {
+      "epoch": 0.08307501549907005,
+      "grad_norm": 3.0964016914367676,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.3271,
+      "step": 67
+    },
+    {
+      "epoch": 0.08431494110353378,
+      "grad_norm": 3.8873424530029297,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.2556,
+      "step": 68
+    },
+    {
+      "epoch": 0.08555486670799752,
+      "grad_norm": 2.3811612129211426,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.3136,
+      "step": 69
+    },
+    {
+      "epoch": 0.08679479231246125,
+      "grad_norm": 4.680008411407471,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6543,
+      "step": 70
+    },
+    {
+      "epoch": 0.08803471791692498,
+      "grad_norm": 3.486687183380127,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.5671,
+      "step": 71
+    },
+    {
+      "epoch": 0.08927464352138871,
+      "grad_norm": 2.453212261199951,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.1672,
+      "step": 72
+    },
+    {
+      "epoch": 0.08927464352138871,
+      "eval_loss": 0.3752855658531189,
+      "eval_runtime": 74.5418,
+      "eval_samples_per_second": 9.109,
+      "eval_steps_per_second": 1.14,
+      "step": 72
+    },
+    {
+      "epoch": 0.09051456912585244,
+      "grad_norm": 4.2769951820373535,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.285,
+      "step": 73
+    },
+    {
+      "epoch": 0.09175449473031617,
+      "grad_norm": 3.424060106277466,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.4328,
+      "step": 74
+    },
+    {
+      "epoch": 0.0929944203347799,
+      "grad_norm": 3.5395214557647705,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4982,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 5.56415462670336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null