Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a75c95b5aa5cbd938d68b35da3fcd50cc4a17e9a3a1a3b5b722b9c0dd47fe3
+oid sha256:0cfe5ed253326636ede1ba97f5b0b93618f659831083ffc3c769280e8969d645
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f375b4408b6af3d228fa080ea22911a918cc4147b4e684b0dc75a73f51b3576
+oid sha256:56775d698fb2783416f108ba153efe22206e0afc17b5cdde67a702e9714fff58
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
+oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
 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": 0.00578368999421631,
+  "epoch": 0.008675534991324466,
   "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": 1.3744,
       "step": 50
+    },
+    {
+      "epoch": 0.005899363794100636,
+      "grad_norm": 0.5805677175521851,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.5171,
+      "step": 51
+    },
+    {
+      "epoch": 0.006015037593984963,
+      "grad_norm": 0.7673519849777222,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.539,
+      "step": 52
+    },
+    {
+      "epoch": 0.006130711393869288,
+      "grad_norm": 0.6361537575721741,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.3872,
+      "step": 53
+    },
+    {
+      "epoch": 0.006246385193753615,
+      "grad_norm": 0.6733700037002563,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3519,
+      "step": 54
+    },
+    {
+      "epoch": 0.006246385193753615,
+      "eval_loss": 1.3062171936035156,
+      "eval_runtime": 740.203,
+      "eval_samples_per_second": 9.835,
+      "eval_steps_per_second": 1.229,
+      "step": 54
+    },
+    {
+      "epoch": 0.006362058993637941,
+      "grad_norm": 0.7923408150672913,
+      "learning_rate": 5e-05,
+      "loss": 1.551,
+      "step": 55
+    },
+    {
+      "epoch": 0.006477732793522267,
+      "grad_norm": 0.5155686140060425,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.3645,
+      "step": 56
+    },
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 0.5228220820426941,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.1924,
+      "step": 57
+    },
+    {
+      "epoch": 0.00670908039329092,
+      "grad_norm": 0.532507598400116,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3401,
+      "step": 58
+    },
+    {
+      "epoch": 0.0068247541931752455,
+      "grad_norm": 0.502334713935852,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.4,
+      "step": 59
+    },
+    {
+      "epoch": 0.006940427993059572,
+      "grad_norm": 0.5452474355697632,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3153,
+      "step": 60
+    },
+    {
+      "epoch": 0.007056101792943898,
+      "grad_norm": 0.5242115259170532,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.2159,
+      "step": 61
+    },
+    {
+      "epoch": 0.007171775592828224,
+      "grad_norm": 0.5378577709197998,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.4083,
+      "step": 62
+    },
+    {
+      "epoch": 0.0072874493927125505,
+      "grad_norm": 0.6914247870445251,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.4672,
+      "step": 63
+    },
+    {
+      "epoch": 0.0072874493927125505,
+      "eval_loss": 1.2972004413604736,
+      "eval_runtime": 740.0228,
+      "eval_samples_per_second": 9.838,
+      "eval_steps_per_second": 1.23,
+      "step": 63
+    },
+    {
+      "epoch": 0.007403123192596877,
+      "grad_norm": 0.44368940591812134,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.2916,
+      "step": 64
+    },
+    {
+      "epoch": 0.007518796992481203,
+      "grad_norm": 0.9511928558349609,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.263,
+      "step": 65
+    },
+    {
+      "epoch": 0.007634470792365529,
+      "grad_norm": 0.5774746537208557,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.3052,
+      "step": 66
+    },
+    {
+      "epoch": 0.0077501445922498555,
+      "grad_norm": 0.46265479922294617,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.9235,
+      "step": 67
+    },
+    {
+      "epoch": 0.007865818392134181,
+      "grad_norm": 0.41311484575271606,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.2072,
+      "step": 68
+    },
+    {
+      "epoch": 0.007981492192018508,
+      "grad_norm": 0.7407188415527344,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.4064,
+      "step": 69
+    },
+    {
+      "epoch": 0.008097165991902834,
+      "grad_norm": 0.6462542414665222,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.581,
+      "step": 70
+    },
+    {
+      "epoch": 0.00821283979178716,
+      "grad_norm": 0.7185479998588562,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.3954,
+      "step": 71
+    },
+    {
+      "epoch": 0.008328513591671487,
+      "grad_norm": 0.5311028957366943,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.4774,
+      "step": 72
+    },
+    {
+      "epoch": 0.008328513591671487,
+      "eval_loss": 1.2917875051498413,
+      "eval_runtime": 740.0809,
+      "eval_samples_per_second": 9.837,
+      "eval_steps_per_second": 1.23,
+      "step": 72
+    },
+    {
+      "epoch": 0.008444187391555813,
+      "grad_norm": 0.576357364654541,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.3201,
+      "step": 73
+    },
+    {
+      "epoch": 0.008559861191440138,
+      "grad_norm": 0.4944629669189453,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2015,
+      "step": 74
+    },
+    {
+      "epoch": 0.008675534991324466,
+      "grad_norm": 0.5077426433563232,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.0517,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3054705844224e+16,
+  "total_flos": 4.9582058766336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null