Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e4a964f31dd0a8dd5f1cbfa36c04b66c899e2ddf60b4412ae882c81f3e50580
+oid sha256:1df23eba55a0e64c6381d93121391a66deb947d7ab328c15fda79fff94d3911d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ddb04398fa4312eac567eaeeb7b06131658bcad362ffe49a8d216090472ce4
+oid sha256:e5b0d82c8ca872af92dc16fd9c789f946a211515a37f16b24107d76b6ecb6f73
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea6542ea5e34bb1c1dcc0aa12c7426317df18665467f05291c0133229c6e57f4
+oid sha256:7ec3466ebef9ba9a998d326b382a663538569d6f8034c03944a4efb1b32160f5
 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": 0.4608294930875576,
+  "epoch": 0.6912442396313364,
   "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": 0.8966,
       "step": 50
+    },
+    {
+      "epoch": 0.4700460829493088,
+      "grad_norm": 0.7265362739562988,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.0726,
+      "step": 51
+    },
+    {
+      "epoch": 0.4792626728110599,
+      "grad_norm": 0.6666373610496521,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.9776,
+      "step": 52
+    },
+    {
+      "epoch": 0.48847926267281105,
+      "grad_norm": 1.1823261976242065,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.0739,
+      "step": 53
+    },
+    {
+      "epoch": 0.4976958525345622,
+      "grad_norm": 0.7592246532440186,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.9637,
+      "step": 54
+    },
+    {
+      "epoch": 0.4976958525345622,
+      "eval_loss": 1.0075299739837646,
+      "eval_runtime": 11.0761,
+      "eval_samples_per_second": 8.306,
+      "eval_steps_per_second": 1.083,
+      "step": 54
+    },
+    {
+      "epoch": 0.5069124423963134,
+      "grad_norm": 0.9630380868911743,
+      "learning_rate": 5e-05,
+      "loss": 1.1823,
+      "step": 55
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.8581224679946899,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.9804,
+      "step": 56
+    },
+    {
+      "epoch": 0.5253456221198156,
+      "grad_norm": 0.72942715883255,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0405,
+      "step": 57
+    },
+    {
+      "epoch": 0.5345622119815668,
+      "grad_norm": 0.7310763001441956,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.9986,
+      "step": 58
+    },
+    {
+      "epoch": 0.543778801843318,
+      "grad_norm": 0.8449254035949707,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.9641,
+      "step": 59
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 0.8063848614692688,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.9988,
+      "step": 60
+    },
+    {
+      "epoch": 0.5622119815668203,
+      "grad_norm": 0.9789047837257385,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.0653,
+      "step": 61
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.8241631388664246,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.0918,
+      "step": 62
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 1.76102876663208,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.1036,
+      "step": 63
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "eval_loss": 0.9918219447135925,
+      "eval_runtime": 11.0869,
+      "eval_samples_per_second": 8.298,
+      "eval_steps_per_second": 1.082,
+      "step": 63
+    },
+    {
+      "epoch": 0.5898617511520737,
+      "grad_norm": 0.57708740234375,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.9456,
+      "step": 64
+    },
+    {
+      "epoch": 0.5990783410138248,
+      "grad_norm": 0.8000180721282959,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.8919,
+      "step": 65
+    },
+    {
+      "epoch": 0.6082949308755761,
+      "grad_norm": 0.759195864200592,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.921,
+      "step": 66
+    },
+    {
+      "epoch": 0.6175115207373272,
+      "grad_norm": 0.7203258872032166,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.987,
+      "step": 67
+    },
+    {
+      "epoch": 0.6267281105990783,
+      "grad_norm": 1.042421817779541,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.1359,
+      "step": 68
+    },
+    {
+      "epoch": 0.6359447004608295,
+      "grad_norm": 0.7227110266685486,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.9977,
+      "step": 69
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.127,
+      "step": 70
+    },
+    {
+      "epoch": 0.6543778801843319,
+      "grad_norm": 0.7786197662353516,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.0038,
+      "step": 71
+    },
+    {
+      "epoch": 0.663594470046083,
+      "grad_norm": 0.8227571845054626,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0009,
+      "step": 72
+    },
+    {
+      "epoch": 0.663594470046083,
+      "eval_loss": 0.9819597005844116,
+      "eval_runtime": 11.0775,
+      "eval_samples_per_second": 8.305,
+      "eval_steps_per_second": 1.083,
+      "step": 72
+    },
+    {
+      "epoch": 0.6728110599078341,
+      "grad_norm": 1.0306525230407715,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.0768,
+      "step": 73
+    },
+    {
+      "epoch": 0.6820276497695853,
+      "grad_norm": 0.6918361186981201,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8636,
+      "step": 74
+    },
+    {
+      "epoch": 0.6912442396313364,
+      "grad_norm": 0.8258764147758484,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.9472,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.932002602870374e+16,
+  "total_flos": 5.935098268483584e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null