Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15adf756fd8d29ee33087651b79bd8bfbe85dcd317cd3623da4a14da763b855e
+oid sha256:185f086f22f385c92df728d926d88f92b3966675c29ee7943d1058d42d0a5ca1
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d722d182e6f0cd3937dca970888df5afb8b4b8576cb0374a50418f7f04176a3
+oid sha256:88a71bc2eeae32e4c96c9f659c825ff481f23d9c49df07b993538276e451b211
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274bad6912abd00f7939e88b2927c448da73420ebf4efa2b0a54eb2c00324194
+oid sha256:d24d2e8e76f08f48de18a7fab9b899f70eefc96fde5f6bcaf00a77bccbaf0ea5
 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": 0.006867660188173889,
+  "epoch": 0.010301490282260834,
   "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": 0.2989,
       "step": 50
+    },
+    {
+      "epoch": 0.007005013391937367,
+      "grad_norm": 2.5533089637756348,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2884,
+      "step": 51
+    },
+    {
+      "epoch": 0.007142366595700844,
+      "grad_norm": 1.415504813194275,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1548,
+      "step": 52
+    },
+    {
+      "epoch": 0.0072797197994643225,
+      "grad_norm": 2.212552309036255,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.1524,
+      "step": 53
+    },
+    {
+      "epoch": 0.0074170730032278006,
+      "grad_norm": 2.2554523944854736,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.1038,
+      "step": 54
+    },
+    {
+      "epoch": 0.0074170730032278006,
+      "eval_loss": 0.24693803489208221,
+      "eval_runtime": 1498.651,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 0.512,
+      "step": 54
+    },
+    {
+      "epoch": 0.007554426206991278,
+      "grad_norm": 4.748584270477295,
+      "learning_rate": 5e-05,
+      "loss": 0.2923,
+      "step": 55
+    },
+    {
+      "epoch": 0.007691779410754756,
+      "grad_norm": 3.5152838230133057,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1623,
+      "step": 56
+    },
+    {
+      "epoch": 0.007829132614518234,
+      "grad_norm": 3.639317274093628,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.1558,
+      "step": 57
+    },
+    {
+      "epoch": 0.007966485818281712,
+      "grad_norm": 1.4831420183181763,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0574,
+      "step": 58
+    },
+    {
+      "epoch": 0.008103839022045188,
+      "grad_norm": 3.9552788734436035,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.1435,
+      "step": 59
+    },
+    {
+      "epoch": 0.008241192225808667,
+      "grad_norm": 5.947100639343262,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2129,
+      "step": 60
+    },
+    {
+      "epoch": 0.008378545429572145,
+      "grad_norm": 4.984751224517822,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1273,
+      "step": 61
+    },
+    {
+      "epoch": 0.008515898633335623,
+      "grad_norm": 3.6993088722229004,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.1048,
+      "step": 62
+    },
+    {
+      "epoch": 0.0086532518370991,
+      "grad_norm": 4.781378746032715,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1657,
+      "step": 63
+    },
+    {
+      "epoch": 0.0086532518370991,
+      "eval_loss": 0.18375518918037415,
+      "eval_runtime": 1499.3899,
+      "eval_samples_per_second": 4.089,
+      "eval_steps_per_second": 0.512,
+      "step": 63
+    },
+    {
+      "epoch": 0.008790605040862579,
+      "grad_norm": 3.943474054336548,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1574,
+      "step": 64
+    },
+    {
+      "epoch": 0.008927958244626055,
+      "grad_norm": 6.085975170135498,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.2722,
+      "step": 65
+    },
+    {
+      "epoch": 0.009065311448389533,
+      "grad_norm": 6.4064717292785645,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2512,
+      "step": 66
+    },
+    {
+      "epoch": 0.009202664652153011,
+      "grad_norm": 2.87799072265625,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.108,
+      "step": 67
+    },
+    {
+      "epoch": 0.00934001785591649,
+      "grad_norm": 8.213472366333008,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.472,
+      "step": 68
+    },
+    {
+      "epoch": 0.009477371059679968,
+      "grad_norm": 3.442542791366577,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0854,
+      "step": 69
+    },
+    {
+      "epoch": 0.009614724263443444,
+      "grad_norm": 6.024069309234619,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3747,
+      "step": 70
+    },
+    {
+      "epoch": 0.009752077467206922,
+      "grad_norm": 2.477121114730835,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0355,
+      "step": 71
+    },
+    {
+      "epoch": 0.0098894306709704,
+      "grad_norm": 5.309243679046631,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0862,
+      "step": 72
+    },
+    {
+      "epoch": 0.0098894306709704,
+      "eval_loss": 0.1321064531803131,
+      "eval_runtime": 1498.0742,
+      "eval_samples_per_second": 4.093,
+      "eval_steps_per_second": 0.512,
+      "step": 72
+    },
+    {
+      "epoch": 0.010026783874733878,
+      "grad_norm": 6.38518762588501,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0985,
+      "step": 73
+    },
+    {
+      "epoch": 0.010164137078497356,
+      "grad_norm": 0.5211701989173889,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0106,
+      "step": 74
+    },
+    {
+      "epoch": 0.010301490282260834,
+      "grad_norm": 3.0065691471099854,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1057,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.617690146471936e+16,
+  "total_flos": 3.918303489687552e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null