Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0e6b0986306528a714890b8654e9051e795b9f67acc607435480b185a7170e
+oid sha256:3b68b02026392f6c63898d35bb0d8fb7819b1b21c86fa63a94b7f987ddd13204
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8817c89e6dc92959d19253578b2dac871909a78b2e586af1193abf6ba2078d07
+oid sha256:9f7a0a65dc31a0ce005dd0554a933f8c357a6b95847aaf53ebc48a5c9bd1b810
 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": 0.0016722128392501797,
+  "epoch": 0.0025083192588752695,
   "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": 1.3558,
       "step": 50
+    },
+    {
+      "epoch": 0.0017056570960351835,
+      "grad_norm": 2.009683132171631,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.3781,
+      "step": 51
+    },
+    {
+      "epoch": 0.001739101352820187,
+      "grad_norm": 1.7342225313186646,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5557,
+      "step": 52
+    },
+    {
+      "epoch": 0.0017725456096051905,
+      "grad_norm": 1.5290874242782593,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.3127,
+      "step": 53
+    },
+    {
+      "epoch": 0.0018059898663901942,
+      "grad_norm": 1.653159499168396,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1634,
+      "step": 54
+    },
+    {
+      "epoch": 0.0018059898663901942,
+      "eval_loss": 1.3522837162017822,
+      "eval_runtime": 2739.9035,
+      "eval_samples_per_second": 9.19,
+      "eval_steps_per_second": 1.149,
+      "step": 54
+    },
+    {
+      "epoch": 0.0018394341231751977,
+      "grad_norm": 1.6415021419525146,
+      "learning_rate": 5e-05,
+      "loss": 1.4116,
+      "step": 55
+    },
+    {
+      "epoch": 0.0018728783799602012,
+      "grad_norm": 1.749309778213501,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.4152,
+      "step": 56
+    },
+    {
+      "epoch": 0.001906322636745205,
+      "grad_norm": 1.564772367477417,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.417,
+      "step": 57
+    },
+    {
+      "epoch": 0.0019397668935302085,
+      "grad_norm": 1.849936842918396,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3394,
+      "step": 58
+    },
+    {
+      "epoch": 0.001973211150315212,
+      "grad_norm": 1.7286560535430908,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.5013,
+      "step": 59
+    },
+    {
+      "epoch": 0.0020066554071002155,
+      "grad_norm": 1.9632574319839478,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3443,
+      "step": 60
+    },
+    {
+      "epoch": 0.0020400996638852194,
+      "grad_norm": 1.7394282817840576,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.3558,
+      "step": 61
+    },
+    {
+      "epoch": 0.002073543920670223,
+      "grad_norm": 2.260873794555664,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3278,
+      "step": 62
+    },
+    {
+      "epoch": 0.0021069881774552265,
+      "grad_norm": 1.8529855012893677,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.2319,
+      "step": 63
+    },
+    {
+      "epoch": 0.0021069881774552265,
+      "eval_loss": 1.3400989770889282,
+      "eval_runtime": 2741.0245,
+      "eval_samples_per_second": 9.186,
+      "eval_steps_per_second": 1.148,
+      "step": 63
+    },
+    {
+      "epoch": 0.00214043243424023,
+      "grad_norm": 1.778730034828186,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3719,
+      "step": 64
+    },
+    {
+      "epoch": 0.0021738766910252335,
+      "grad_norm": 1.7320828437805176,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.3139,
+      "step": 65
+    },
+    {
+      "epoch": 0.0022073209478102374,
+      "grad_norm": 1.8604722023010254,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.1788,
+      "step": 66
+    },
+    {
+      "epoch": 0.002240765204595241,
+      "grad_norm": 2.2654762268066406,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.4146,
+      "step": 67
+    },
+    {
+      "epoch": 0.0022742094613802445,
+      "grad_norm": 1.7686560153961182,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.2696,
+      "step": 68
+    },
+    {
+      "epoch": 0.002307653718165248,
+      "grad_norm": 1.5691628456115723,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.2514,
+      "step": 69
+    },
+    {
+      "epoch": 0.0023410979749502515,
+      "grad_norm": 1.543271541595459,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4583,
+      "step": 70
+    },
+    {
+      "epoch": 0.0023745422317352554,
+      "grad_norm": 1.897420048713684,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.3972,
+      "step": 71
+    },
+    {
+      "epoch": 0.002407986488520259,
+      "grad_norm": 1.782452940940857,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.4984,
+      "step": 72
+    },
+    {
+      "epoch": 0.002407986488520259,
+      "eval_loss": 1.331598162651062,
+      "eval_runtime": 2742.8962,
+      "eval_samples_per_second": 9.18,
+      "eval_steps_per_second": 1.148,
+      "step": 72
+    },
+    {
+      "epoch": 0.0024414307453052625,
+      "grad_norm": 1.812255620956421,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.3558,
+      "step": 73
+    },
+    {
+      "epoch": 0.002474875002090266,
+      "grad_norm": 1.7149916887283325,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2338,
+      "step": 74
+    },
+    {
+      "epoch": 0.0025083192588752695,
+      "grad_norm": 1.5673575401306152,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.5045,
+      "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