Training in progress, step 84, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421d33d054daeb271659f629f667a37ecef24e273e8dfa833bcde0144fc04530
+oid sha256:88a479e925ede0c3da3821d664013f8c545b67f4c0210547884d9612a19eef4f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f931aa37152dedf153064b3be0776d8e1dacee8778f5d5df791f5d97f83e6a74
+oid sha256:27a7e3cd7b75a685cbd36c0f64b79a56218ed9625b7edaae67dc35cc2696380b
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543a07122da3e253f249468a50ec3be9293aece3c127574755dcffd0eea2d380
+oid sha256:ab838fbe570b6d415c10780e3a0e3a3e25daa76549fd9a5954f6f1727ad17437
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24225e147d7b9425c760fd15a44cb007389a8d29dfe49f25bc43f19fd631f65
+oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13680781758957655,
+  "epoch": 0.2736156351791531,
   "eval_steps": 42,
-  "global_step": 42,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,112 @@
       "eval_samples_per_second": 23.359,
       "eval_steps_per_second": 5.874,
       "step": 42
+    },
+    {
+      "epoch": 0.1465798045602606,
+      "grad_norm": 2.9569833278656006,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 1.6317,
+      "step": 45
+    },
+    {
+      "epoch": 0.1563517915309446,
+      "grad_norm": 2.9722719192504883,
+      "learning_rate": 9.852339101019574e-05,
+      "loss": 1.4734,
+      "step": 48
+    },
+    {
+      "epoch": 0.16612377850162866,
+      "grad_norm": 3.663701295852661,
+      "learning_rate": 9.828243544427796e-05,
+      "loss": 1.7673,
+      "step": 51
+    },
+    {
+      "epoch": 0.1758957654723127,
+      "grad_norm": 2.7686305046081543,
+      "learning_rate": 9.802361805155097e-05,
+      "loss": 1.5428,
+      "step": 54
+    },
+    {
+      "epoch": 0.18566775244299674,
+      "grad_norm": 2.781644582748413,
+      "learning_rate": 9.774703458011453e-05,
+      "loss": 1.7697,
+      "step": 57
+    },
+    {
+      "epoch": 0.19543973941368079,
+      "grad_norm": 2.7254538536071777,
+      "learning_rate": 9.745278735053343e-05,
+      "loss": 1.5856,
+      "step": 60
+    },
+    {
+      "epoch": 0.20521172638436483,
+      "grad_norm": 2.544527769088745,
+      "learning_rate": 9.714098521798465e-05,
+      "loss": 1.5917,
+      "step": 63
+    },
+    {
+      "epoch": 0.21498371335504887,
+      "grad_norm": 3.226173162460327,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 1.5432,
+      "step": 66
+    },
+    {
+      "epoch": 0.2247557003257329,
+      "grad_norm": 2.7061498165130615,
+      "learning_rate": 9.64651840937276e-05,
+      "loss": 1.6754,
+      "step": 69
+    },
+    {
+      "epoch": 0.23452768729641693,
+      "grad_norm": 2.9291999340057373,
+      "learning_rate": 9.610143511100354e-05,
+      "loss": 1.5638,
+      "step": 72
+    },
+    {
+      "epoch": 0.24429967426710097,
+      "grad_norm": 2.4796836376190186,
+      "learning_rate": 9.572063115079063e-05,
+      "loss": 1.474,
+      "step": 75
+    },
+    {
+      "epoch": 0.254071661237785,
+      "grad_norm": 2.7676734924316406,
+      "learning_rate": 9.53229130894619e-05,
+      "loss": 1.5904,
+      "step": 78
+    },
+    {
+      "epoch": 0.26384364820846906,
+      "grad_norm": 2.8210036754608154,
+      "learning_rate": 9.490842806067095e-05,
+      "loss": 1.6858,
+      "step": 81
+    },
+    {
+      "epoch": 0.2736156351791531,
+      "grad_norm": 2.67210054397583,
+      "learning_rate": 9.44773294009206e-05,
+      "loss": 1.5434,
+      "step": 84
+    },
+    {
+      "epoch": 0.2736156351791531,
+      "eval_loss": 1.6323200464248657,
+      "eval_runtime": 22.1692,
+      "eval_samples_per_second": 23.321,
+      "eval_steps_per_second": 5.864,
+      "step": 84
     }
   ],
   "logging_steps": 3,
@@ -140,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1678785153662976e+16,
+  "total_flos": 6.335757030732595e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null