Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f31796c4370254d6e20af3a4bd9050f4efb870b3205f7224d96093838d7db0c
+oid sha256:d98d380e2ef25ebe15f834feeeceeaaa5a1259ad9e106311f8a62327fc02c996
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb77e550360b1cd3a584ae6e364bd2cdeb90bb658893b4adbad1abdeab7749f
+oid sha256:f7b8b4b5d4e61ae376da175312d3f51fa09b4833c20d2acaa0e802d9ceafbd55
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d841eda044e2a0b4625c1a49f398ba41b30f358c4216b4153690415e794a13
+oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
 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": 0.04764173415912339,
+  "epoch": 0.07146260123868509,
   "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": 2.003,
       "step": 50
+    },
+    {
+      "epoch": 0.04859456884230586,
+      "grad_norm": 1.0506590604782104,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.2448,
+      "step": 51
+    },
+    {
+      "epoch": 0.04954740352548833,
+      "grad_norm": 1.165993571281433,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.057,
+      "step": 52
+    },
+    {
+      "epoch": 0.0505002382086708,
+      "grad_norm": 1.1454460620880127,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.043,
+      "step": 53
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "grad_norm": 1.139070987701416,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.441,
+      "step": 54
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "eval_loss": 2.270153522491455,
+      "eval_runtime": 195.4006,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.568,
+      "step": 54
+    },
+    {
+      "epoch": 0.05240590757503573,
+      "grad_norm": 1.4192317724227905,
+      "learning_rate": 5e-05,
+      "loss": 2.1888,
+      "step": 55
+    },
+    {
+      "epoch": 0.0533587422582182,
+      "grad_norm": 1.4029229879379272,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.6344,
+      "step": 56
+    },
+    {
+      "epoch": 0.054311576941400666,
+      "grad_norm": 1.2530521154403687,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.2003,
+      "step": 57
+    },
+    {
+      "epoch": 0.055264411624583135,
+      "grad_norm": 8.52709674835205,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0568,
+      "step": 58
+    },
+    {
+      "epoch": 0.0562172463077656,
+      "grad_norm": 1.2079765796661377,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.2747,
+      "step": 59
+    },
+    {
+      "epoch": 0.05717008099094807,
+      "grad_norm": 1.1588507890701294,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.4211,
+      "step": 60
+    },
+    {
+      "epoch": 0.05812291567413054,
+      "grad_norm": 1.0553061962127686,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.2825,
+      "step": 61
+    },
+    {
+      "epoch": 0.05907575035731301,
+      "grad_norm": 0.9334769248962402,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2447,
+      "step": 62
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "grad_norm": 1.0937581062316895,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.024,
+      "step": 63
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "eval_loss": 2.261378049850464,
+      "eval_runtime": 195.3363,
+      "eval_samples_per_second": 4.526,
+      "eval_steps_per_second": 0.568,
+      "step": 63
+    },
+    {
+      "epoch": 0.06098141972367794,
+      "grad_norm": 2.8231825828552246,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3215,
+      "step": 64
+    },
+    {
+      "epoch": 0.06193425440686041,
+      "grad_norm": 1.4724355936050415,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.1722,
+      "step": 65
+    },
+    {
+      "epoch": 0.06288708909004288,
+      "grad_norm": 4.071575164794922,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2437,
+      "step": 66
+    },
+    {
+      "epoch": 0.06383992377322535,
+      "grad_norm": 1.1286451816558838,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.1099,
+      "step": 67
+    },
+    {
+      "epoch": 0.06479275845640782,
+      "grad_norm": 1.3559694290161133,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.261,
+      "step": 68
+    },
+    {
+      "epoch": 0.06574559313959027,
+      "grad_norm": 1.2074459791183472,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.172,
+      "step": 69
+    },
+    {
+      "epoch": 0.06669842782277274,
+      "grad_norm": 1.2289658784866333,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3035,
+      "step": 70
+    },
+    {
+      "epoch": 0.06765126250595521,
+      "grad_norm": 1.2221287488937378,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.2006,
+      "step": 71
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "grad_norm": 1.2182445526123047,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2886,
+      "step": 72
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "eval_loss": 2.2531282901763916,
+      "eval_runtime": 195.3498,
+      "eval_samples_per_second": 4.525,
+      "eval_steps_per_second": 0.568,
+      "step": 72
+    },
+    {
+      "epoch": 0.06955693187232015,
+      "grad_norm": 0.7799471020698547,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0113,
+      "step": 73
+    },
+    {
+      "epoch": 0.07050976655550262,
+      "grad_norm": 0.9231268763542175,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1421,
+      "step": 74
+    },
+    {
+      "epoch": 0.07146260123868509,
+      "grad_norm": 0.8884665966033936,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1019,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.41887283560448e+16,
+  "total_flos": 1.112830925340672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null