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:c5727aed7264895ce483e3134fbb2b431bf979e4ce5f8dca7474305ae25cb545
+oid sha256:f96fe0f77223bf21e72bb8cec824d6e8118b382aeb4fe8d6ab68534e260cbf8d
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c570c5c3aa5eebbe9d69815e16860b95f7b21fa85b9d5b528b7e153ad5e5cf
+oid sha256:b9ecd8d4edbc1eb01635b7969b0317e2e2ac7ee4e46b9c2667bf035cf5a6df33
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a75ae50ef05b0af49c3969f35c925149f1546408e414606cff98807664e1d74
+oid sha256:103b84660003cbb55211ca46c75dea4086b05940b67e924565c8120dfc91f67a
 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": 0.1188118811881188,
+  "epoch": 0.2376237623762376,
   "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": 94.125,
       "eval_steps_per_second": 11.845,
       "step": 42
+    },
+    {
+      "epoch": 0.1272984441301273,
+      "grad_norm": 0.20692946016788483,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 11.8396,
+      "step": 45
+    },
+    {
+      "epoch": 0.13578500707213578,
+      "grad_norm": 0.23685254156589508,
+      "learning_rate": 9.852339101019574e-05,
+      "loss": 11.8316,
+      "step": 48
+    },
+    {
+      "epoch": 0.14427157001414428,
+      "grad_norm": 0.2432631552219391,
+      "learning_rate": 9.828243544427796e-05,
+      "loss": 11.8341,
+      "step": 51
+    },
+    {
+      "epoch": 0.15275813295615276,
+      "grad_norm": 0.11745542287826538,
+      "learning_rate": 9.802361805155097e-05,
+      "loss": 11.8301,
+      "step": 54
+    },
+    {
+      "epoch": 0.16124469589816123,
+      "grad_norm": 0.134097158908844,
+      "learning_rate": 9.774703458011453e-05,
+      "loss": 11.8359,
+      "step": 57
+    },
+    {
+      "epoch": 0.16973125884016974,
+      "grad_norm": 0.19680051505565643,
+      "learning_rate": 9.745278735053343e-05,
+      "loss": 11.8378,
+      "step": 60
+    },
+    {
+      "epoch": 0.1782178217821782,
+      "grad_norm": 0.10566498339176178,
+      "learning_rate": 9.714098521798465e-05,
+      "loss": 11.832,
+      "step": 63
+    },
+    {
+      "epoch": 0.1867043847241867,
+      "grad_norm": 0.1530551165342331,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 11.8363,
+      "step": 66
+    },
+    {
+      "epoch": 0.19519094766619519,
+      "grad_norm": 0.1929464042186737,
+      "learning_rate": 9.64651840937276e-05,
+      "loss": 11.8284,
+      "step": 69
+    },
+    {
+      "epoch": 0.2036775106082037,
+      "grad_norm": 0.17411480844020844,
+      "learning_rate": 9.610143511100354e-05,
+      "loss": 11.8314,
+      "step": 72
+    },
+    {
+      "epoch": 0.21216407355021216,
+      "grad_norm": 0.14971987903118134,
+      "learning_rate": 9.572063115079063e-05,
+      "loss": 11.832,
+      "step": 75
+    },
+    {
+      "epoch": 0.22065063649222066,
+      "grad_norm": 0.18370923399925232,
+      "learning_rate": 9.53229130894619e-05,
+      "loss": 11.8275,
+      "step": 78
+    },
+    {
+      "epoch": 0.22913719943422914,
+      "grad_norm": 0.26103201508522034,
+      "learning_rate": 9.490842806067095e-05,
+      "loss": 11.8278,
+      "step": 81
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 0.21483545005321503,
+      "learning_rate": 9.44773294009206e-05,
+      "loss": 11.825,
+      "step": 84
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "eval_loss": 11.825268745422363,
+      "eval_runtime": 6.402,
+      "eval_samples_per_second": 93.097,
+      "eval_steps_per_second": 11.715,
+      "step": 84
     }
   ],
   "logging_steps": 3,
@@ -140,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 254298685440.0,
+  "total_flos": 503776542720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null