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:ae84fd3f31e151654ac1b73f89b555b426cf1db67b5c6045c4ecff4e9af9a697
+oid sha256:456253c7b47d4b3c8243274d8f1190016149670c15112b9fcc626948b11c7602
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8181b5cf2858ef70571b079be880a592072c65abe5cb38e3b97de3fadda9c952
+oid sha256:b2fc91c6b00712bbf4e7a0192024ffcb8366e804e7151ebbd3e63f1094526645
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906a9e6400187d6899fb20f1e1e70a8f191fa21191db7d4f21aaf6ccce3ae8ad
+oid sha256:0f3fac815969f48929052743a5a69cb3dfca2432072712e9113166288361420c
 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": 0.0027010236879777437,
+  "epoch": 0.004051535531966615,
   "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": 1.4374,
       "step": 50
+    },
+    {
+      "epoch": 0.0027550441617372984,
+      "grad_norm": 1.039516568183899,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.4768,
+      "step": 51
+    },
+    {
+      "epoch": 0.0028090646354968535,
+      "grad_norm": 0.9859927296638489,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.4673,
+      "step": 52
+    },
+    {
+      "epoch": 0.002863085109256408,
+      "grad_norm": 0.9465391635894775,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.5106,
+      "step": 53
+    },
+    {
+      "epoch": 0.002917105583015963,
+      "grad_norm": 1.1751928329467773,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3325,
+      "step": 54
+    },
+    {
+      "epoch": 0.002917105583015963,
+      "eval_loss": 1.4378173351287842,
+      "eval_runtime": 3370.1952,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 54
+    },
+    {
+      "epoch": 0.002971126056775518,
+      "grad_norm": 1.083316683769226,
+      "learning_rate": 5e-05,
+      "loss": 1.4346,
+      "step": 55
+    },
+    {
+      "epoch": 0.0030251465305350727,
+      "grad_norm": 1.12709641456604,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.51,
+      "step": 56
+    },
+    {
+      "epoch": 0.003079167004294628,
+      "grad_norm": 1.2147878408432007,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.6,
+      "step": 57
+    },
+    {
+      "epoch": 0.0031331874780541826,
+      "grad_norm": 1.0804308652877808,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4287,
+      "step": 58
+    },
+    {
+      "epoch": 0.0031872079518137373,
+      "grad_norm": 0.9167782068252563,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.4368,
+      "step": 59
+    },
+    {
+      "epoch": 0.0032412284255732924,
+      "grad_norm": 1.4328035116195679,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.222,
+      "step": 60
+    },
+    {
+      "epoch": 0.003295248899332847,
+      "grad_norm": 2.311690330505371,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.6455,
+      "step": 61
+    },
+    {
+      "epoch": 0.0033492693730924022,
+      "grad_norm": 0.9619605541229248,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.2385,
+      "step": 62
+    },
+    {
+      "epoch": 0.003403289846851957,
+      "grad_norm": 1.0867960453033447,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.2282,
+      "step": 63
+    },
+    {
+      "epoch": 0.003403289846851957,
+      "eval_loss": 1.4248102903366089,
+      "eval_runtime": 3370.2237,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 63
+    },
+    {
+      "epoch": 0.0034573103206115116,
+      "grad_norm": 1.1048400402069092,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.4752,
+      "step": 64
+    },
+    {
+      "epoch": 0.0035113307943710668,
+      "grad_norm": 0.9802713990211487,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.4726,
+      "step": 65
+    },
+    {
+      "epoch": 0.0035653512681306215,
+      "grad_norm": 0.8620728850364685,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.2183,
+      "step": 66
+    },
+    {
+      "epoch": 0.003619371741890176,
+      "grad_norm": 0.8618316054344177,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.3536,
+      "step": 67
+    },
+    {
+      "epoch": 0.0036733922156497313,
+      "grad_norm": 0.8729385137557983,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3593,
+      "step": 68
+    },
+    {
+      "epoch": 0.003727412689409286,
+      "grad_norm": 0.898639976978302,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.4913,
+      "step": 69
+    },
+    {
+      "epoch": 0.003781433163168841,
+      "grad_norm": 0.9885318279266357,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4738,
+      "step": 70
+    },
+    {
+      "epoch": 0.003835453636928396,
+      "grad_norm": 0.9679330587387085,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.5127,
+      "step": 71
+    },
+    {
+      "epoch": 0.0038894741106879505,
+      "grad_norm": 0.8212774395942688,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.3274,
+      "step": 72
+    },
+    {
+      "epoch": 0.0038894741106879505,
+      "eval_loss": 1.4179484844207764,
+      "eval_runtime": 3370.1941,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 72
+    },
+    {
+      "epoch": 0.003943494584447506,
+      "grad_norm": 1.0723795890808105,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.5697,
+      "step": 73
+    },
+    {
+      "epoch": 0.003997515058207061,
+      "grad_norm": 0.9993148446083069,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.3406,
+      "step": 74
+    },
+    {
+      "epoch": 0.004051535531966615,
+      "grad_norm": 0.974729061126709,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.4961,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.344684107248435e+16,
+  "total_flos": 1.1017026160872653e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null