Training in progress, step 220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd977cf7243d9c1f34b62b57b65ae2c467137aae625dd14db8a6cd1df7e4639
+oid sha256:379e4bf4bb490ea0b90d9b33347844b50130394e712de1211c8399dedb57115c
 size 1579384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171b376fd04807724ef479a4221c327ea4709dcca15adfcf9297e572211e8b8b
+oid sha256:c3ce2007ab70312728b054080dcbdfaa104c9b8bebf880c9e3901634ded32319
 size 857274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76709219306dc47d70628efaf5fcbc74b4416a92813b7b4f1d01168bd10c9f7c
+oid sha256:76842eb4fcb2a51cac39c00a5e5559ba4d358a8862a4a20b442cc1d7861de163
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c822dec639f0641927f6a0448fd2ae65913fdbdae3d08ed0701aa491ca071f0a
+oid sha256:0fc887555ce5286f8ed809bc469842a587a9d7ef2ff84cb87e5fa06e8f663830
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13206223432792705,
+  "epoch": 0.14526845776071973,
   "eval_steps": 20,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1495,6 +1495,154 @@
       "eval_samples_per_second": 75.365,
       "eval_steps_per_second": 75.365,
       "step": 200
+    },
+    {
+      "epoch": 0.13272254549956666,
+      "grad_norm": 3305.528076171875,
+      "learning_rate": 7.830721146206451e-05,
+      "loss": 92.4619,
+      "step": 201
+    },
+    {
+      "epoch": 0.1333828566712063,
+      "grad_norm": 22266.435546875,
+      "learning_rate": 7.688410249570214e-05,
+      "loss": 90.5834,
+      "step": 202
+    },
+    {
+      "epoch": 0.13404316784284595,
+      "grad_norm": 26988.037109375,
+      "learning_rate": 7.54695740040912e-05,
+      "loss": 86.903,
+      "step": 203
+    },
+    {
+      "epoch": 0.13470347901448557,
+      "grad_norm": 31513.767578125,
+      "learning_rate": 7.406379198842189e-05,
+      "loss": 95.0657,
+      "step": 204
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 28028.66796875,
+      "learning_rate": 7.266692142344672e-05,
+      "loss": 94.906,
+      "step": 205
+    },
+    {
+      "epoch": 0.13602410135776485,
+      "grad_norm": 36479.84375,
+      "learning_rate": 7.127912623811993e-05,
+      "loss": 101.7062,
+      "step": 206
+    },
+    {
+      "epoch": 0.13668441252940447,
+      "grad_norm": 17603.3515625,
+      "learning_rate": 6.990056929635957e-05,
+      "loss": 97.2723,
+      "step": 207
+    },
+    {
+      "epoch": 0.1373447237010441,
+      "grad_norm": 29691.853515625,
+      "learning_rate": 6.853141237793506e-05,
+      "loss": 103.2447,
+      "step": 208
+    },
+    {
+      "epoch": 0.13800503487268376,
+      "grad_norm": 37476.609375,
+      "learning_rate": 6.717181615948126e-05,
+      "loss": 96.3164,
+      "step": 209
+    },
+    {
+      "epoch": 0.1386653460443234,
+      "grad_norm": 34801.02734375,
+      "learning_rate": 6.582194019564266e-05,
+      "loss": 92.4449,
+      "step": 210
+    },
+    {
+      "epoch": 0.13932565721596302,
+      "grad_norm": 16438.6015625,
+      "learning_rate": 6.448194290034848e-05,
+      "loss": 98.2269,
+      "step": 211
+    },
+    {
+      "epoch": 0.13998596838760266,
+      "grad_norm": 39508.171875,
+      "learning_rate": 6.315198152822272e-05,
+      "loss": 86.2956,
+      "step": 212
+    },
+    {
+      "epoch": 0.1406462795592423,
+      "grad_norm": 25744.484375,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 92.17,
+      "step": 213
+    },
+    {
+      "epoch": 0.14130659073088192,
+      "grad_norm": 23628.517578125,
+      "learning_rate": 6.052278966485491e-05,
+      "loss": 84.7765,
+      "step": 214
+    },
+    {
+      "epoch": 0.14196690190252156,
+      "grad_norm": 58147.26953125,
+      "learning_rate": 5.922386772093526e-05,
+      "loss": 98.1311,
+      "step": 215
+    },
+    {
+      "epoch": 0.1426272130741612,
+      "grad_norm": 39249.59765625,
+      "learning_rate": 5.793559875861938e-05,
+      "loss": 85.3396,
+      "step": 216
+    },
+    {
+      "epoch": 0.14328752424580082,
+      "grad_norm": 29692.048828125,
+      "learning_rate": 5.6658133961981894e-05,
+      "loss": 91.5496,
+      "step": 217
+    },
+    {
+      "epoch": 0.14394783541744047,
+      "grad_norm": 49323.46875,
+      "learning_rate": 5.5391623247180744e-05,
+      "loss": 84.2652,
+      "step": 218
+    },
+    {
+      "epoch": 0.1446081465890801,
+      "grad_norm": 43771.90234375,
+      "learning_rate": 5.413621524486363e-05,
+      "loss": 97.1517,
+      "step": 219
+    },
+    {
+      "epoch": 0.14526845776071973,
+      "grad_norm": 37146.6796875,
+      "learning_rate": 5.289205728272586e-05,
+      "loss": 88.1685,
+      "step": 220
+    },
+    {
+      "epoch": 0.14526845776071973,
+      "eval_loss": 9.690956115722656,
+      "eval_runtime": 6.5198,
+      "eval_samples_per_second": 75.923,
+      "eval_steps_per_second": 75.923,
+      "step": 220
     }
   ],
   "logging_steps": 1,
@@ -1514,7 +1662,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 129748728545280.0,
+  "total_flos": 145520653762560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null