Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e409cb8fa744b254b1a8c345ea629dc3b28f081324279756fdc5c325a01c5feb
+oid sha256:1c9d6fa4bd4a7f811d406dc78d71b6277f7a33c87b8dbb1bfc5e8b11944025e3
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ee48e40e6035d9aba926a6f7808928c1169d339755ea3ab6a85192b547dd45
+oid sha256:9b109b4bcd5ed5713f06eb80d62c0cf92f198120ce7084a71f7374bbebfdbbe7
 size 1049049442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3815ae16dc40e74efcece45e896c9f2b9fa451866c099ae3e85989a7d6af3d1
+oid sha256:c94c6399f1cb9c475b90c0c57344eb7d7504723cecd3f0cbfb01bf8e52584025
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9ae45a4a87e9c622f6c946115882b07eb3df1355feb3bb786f6ae49ca483d1
+oid sha256:0ad5f767960ba7d6ae74d9562642b460717a348f4fe2a9ad2bcc901ddcae8168
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2077045440673828,
   "best_model_checkpoint": "./output/checkpoint-1950",
-  "epoch": 0.08734602463605823,
+  "epoch": 0.0940649496080627,
   "eval_steps": 150,
-  "global_step": 1950,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1476,6 +1476,119 @@
       "eval_samples_per_second": 9.666,
       "eval_steps_per_second": 9.666,
       "step": 1950
+    },
+    {
+      "epoch": 0.0877939529675252,
+      "grad_norm": 6.297740459442139,
+      "learning_rate": 5.134936822616837e-06,
+      "loss": 1.1664,
+      "step": 1960
+    },
+    {
+      "epoch": 0.08824188129899216,
+      "grad_norm": 5.478749752044678,
+      "learning_rate": 5.112565447607669e-06,
+      "loss": 1.2503,
+      "step": 1970
+    },
+    {
+      "epoch": 0.08868980963045912,
+      "grad_norm": 4.692316055297852,
+      "learning_rate": 5.090138062869755e-06,
+      "loss": 1.1421,
+      "step": 1980
+    },
+    {
+      "epoch": 0.08913773796192609,
+      "grad_norm": 3.5623536109924316,
+      "learning_rate": 5.067655590305036e-06,
+      "loss": 1.1203,
+      "step": 1990
+    },
+    {
+      "epoch": 0.08958566629339305,
+      "grad_norm": 6.875621318817139,
+      "learning_rate": 5.045118954079904e-06,
+      "loss": 1.1348,
+      "step": 2000
+    },
+    {
+      "epoch": 0.09003359462486002,
+      "grad_norm": 5.2604756355285645,
+      "learning_rate": 5.022529080587205e-06,
+      "loss": 1.0326,
+      "step": 2010
+    },
+    {
+      "epoch": 0.09048152295632698,
+      "grad_norm": 5.012307643890381,
+      "learning_rate": 4.999886898408157e-06,
+      "loss": 1.12,
+      "step": 2020
+    },
+    {
+      "epoch": 0.09092945128779395,
+      "grad_norm": 5.246688365936279,
+      "learning_rate": 4.977193338274189e-06,
+      "loss": 1.1164,
+      "step": 2030
+    },
+    {
+      "epoch": 0.09137737961926092,
+      "grad_norm": 3.9779398441314697,
+      "learning_rate": 4.954449333028672e-06,
+      "loss": 1.0607,
+      "step": 2040
+    },
+    {
+      "epoch": 0.09182530795072788,
+      "grad_norm": 5.392056465148926,
+      "learning_rate": 4.931655817588579e-06,
+      "loss": 1.1102,
+      "step": 2050
+    },
+    {
+      "epoch": 0.09227323628219485,
+      "grad_norm": 5.144470691680908,
+      "learning_rate": 4.9088137289060535e-06,
+      "loss": 1.0649,
+      "step": 2060
+    },
+    {
+      "epoch": 0.09272116461366181,
+      "grad_norm": 3.7060792446136475,
+      "learning_rate": 4.885924005929896e-06,
+      "loss": 1.0718,
+      "step": 2070
+    },
+    {
+      "epoch": 0.09316909294512878,
+      "grad_norm": 3.357794761657715,
+      "learning_rate": 4.862987589566965e-06,
+      "loss": 1.1003,
+      "step": 2080
+    },
+    {
+      "epoch": 0.09361702127659574,
+      "grad_norm": 5.704718589782715,
+      "learning_rate": 4.840005422643503e-06,
+      "loss": 1.2042,
+      "step": 2090
+    },
+    {
+      "epoch": 0.0940649496080627,
+      "grad_norm": 5.481514930725098,
+      "learning_rate": 4.816978449866372e-06,
+      "loss": 1.0777,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0940649496080627,
+      "eval_loss": 1.2093305587768555,
+      "eval_runtime": 51.7975,
+      "eval_samples_per_second": 9.653,
+      "eval_steps_per_second": 9.653,
+      "step": 2100
     }
   ],
   "logging_steps": 10,
@@ -1495,7 +1608,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.518965478232064e+17,
+  "total_flos": 2.72182600608768e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null