Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa6f29e1f10ee8a52b4a38ca4bdb7074dff8129a367f0ee656b939c74e18326
+oid sha256:7f3029cc5bc111deb30744988063e62c23726710f8984b2ef55b7eb163e21412
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d39f8b03e4685e380c0b78cb12198172c8d165527fca11e3d75e0607793d57
+oid sha256:63bb829ef9633f237bd9a661771f908827bc6ba89a79498cabb58d2490575848
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d9923ac95d4aa4a298bd8ed065c1e1d7f9c926e4f6149f930b0b873ca9c5f4
+oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
 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": 0.0023677605720509544,
+  "epoch": 0.003551640858076431,
   "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": 1.6807,
       "step": 50
+    },
+    {
+      "epoch": 0.0024151157834919734,
+      "grad_norm": 6.81873893737793,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.0401,
+      "step": 51
+    },
+    {
+      "epoch": 0.0024624709949329924,
+      "grad_norm": 13.12895679473877,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.5685,
+      "step": 52
+    },
+    {
+      "epoch": 0.0025098262063740114,
+      "grad_norm": 6.2279372215271,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.9409,
+      "step": 53
+    },
+    {
+      "epoch": 0.0025571814178150304,
+      "grad_norm": 7.927605152130127,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.8451,
+      "step": 54
+    },
+    {
+      "epoch": 0.0025571814178150304,
+      "eval_loss": 1.9416064023971558,
+      "eval_runtime": 1958.1372,
+      "eval_samples_per_second": 9.082,
+      "eval_steps_per_second": 1.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.00260453662925605,
+      "grad_norm": 6.186990261077881,
+      "learning_rate": 5e-05,
+      "loss": 2.1235,
+      "step": 55
+    },
+    {
+      "epoch": 0.002651891840697069,
+      "grad_norm": 9.007567405700684,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.8976,
+      "step": 56
+    },
+    {
+      "epoch": 0.002699247052138088,
+      "grad_norm": 12.486298561096191,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.9031,
+      "step": 57
+    },
+    {
+      "epoch": 0.002746602263579107,
+      "grad_norm": 5.143292427062988,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.6532,
+      "step": 58
+    },
+    {
+      "epoch": 0.002793957475020126,
+      "grad_norm": 6.0199689865112305,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.8914,
+      "step": 59
+    },
+    {
+      "epoch": 0.0028413126864611452,
+      "grad_norm": 5.626400947570801,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8248,
+      "step": 60
+    },
+    {
+      "epoch": 0.0028886678979021642,
+      "grad_norm": 6.385285377502441,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.0729,
+      "step": 61
+    },
+    {
+      "epoch": 0.0029360231093431832,
+      "grad_norm": 6.212454319000244,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7437,
+      "step": 62
+    },
+    {
+      "epoch": 0.0029833783207842022,
+      "grad_norm": 7.248876094818115,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.7327,
+      "step": 63
+    },
+    {
+      "epoch": 0.0029833783207842022,
+      "eval_loss": 1.874548316001892,
+      "eval_runtime": 1956.879,
+      "eval_samples_per_second": 9.087,
+      "eval_steps_per_second": 1.136,
+      "step": 63
+    },
+    {
+      "epoch": 0.0030307335322252212,
+      "grad_norm": 9.840112686157227,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2445,
+      "step": 64
+    },
+    {
+      "epoch": 0.0030780887436662407,
+      "grad_norm": 5.413729190826416,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.6007,
+      "step": 65
+    },
+    {
+      "epoch": 0.0031254439551072597,
+      "grad_norm": 12.843977928161621,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.075,
+      "step": 66
+    },
+    {
+      "epoch": 0.0031727991665482787,
+      "grad_norm": 16.38304328918457,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.5473,
+      "step": 67
+    },
+    {
+      "epoch": 0.0032201543779892977,
+      "grad_norm": 9.26452922821045,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.893,
+      "step": 68
+    },
+    {
+      "epoch": 0.0032675095894303167,
+      "grad_norm": 19.458349227905273,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.9362,
+      "step": 69
+    },
+    {
+      "epoch": 0.003314864800871336,
+      "grad_norm": 5.507326126098633,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8801,
+      "step": 70
+    },
+    {
+      "epoch": 0.003362220012312355,
+      "grad_norm": 20.090539932250977,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.1517,
+      "step": 71
+    },
+    {
+      "epoch": 0.003409575223753374,
+      "grad_norm": 13.709304809570312,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2432,
+      "step": 72
+    },
+    {
+      "epoch": 0.003409575223753374,
+      "eval_loss": 1.9207587242126465,
+      "eval_runtime": 1957.5396,
+      "eval_samples_per_second": 9.084,
+      "eval_steps_per_second": 1.136,
+      "step": 72
+    },
+    {
+      "epoch": 0.003456930435194393,
+      "grad_norm": 15.840682029724121,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8682,
+      "step": 73
+    },
+    {
+      "epoch": 0.003504285646635412,
+      "grad_norm": 8.384814262390137,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.7125,
+      "step": 74
+    },
+    {
+      "epoch": 0.003551640858076431,
+      "grad_norm": 8.691859245300293,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.3733,
+      "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