Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dcaeecc4de943ff3b1b25e2080130d8e204326396f2c8274b395a49f7f5b0bc
+oid sha256:e4350d345d97b56ca7b59dbc011925ec1904d8a564b4e38969c9579b074ff804
 size 98088784

last-checkpoint/global_step2150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a44a13ae97270c3c416f31cb0b1f80f12d2017b4f0d8cf1c6268d7d80a8a9e
+size 73939813

last-checkpoint/global_step2150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad29f1a01bca6c52caaba5da3ca1b1b7fed1b150ff1a8a793f96d09e741d822
+size 73939813

last-checkpoint/global_step2150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c041692ece9873bd47a7b865469cc75af6eb0d6bfb4e97d45a24abb258e8a50c
+size 73939877

last-checkpoint/global_step2150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b262ba0035994932655c5a03030ca63c65a5e37551cbdff4a83db6e4eba9ca2
+size 73939877

last-checkpoint/global_step2150/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef2a5d14ad0f0ccc005eeb930f4717339e689bc4df3778a18b1154417ee6b78
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2100
+global_step2150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2637efe7ae6c7cccd9f62f625e99a8a78ee05c5b5f326094b177b4c7a2f01e1f
+oid sha256:065a50993eba0212276345f76d8268040ff81f0b0379c2af74bb3ae5b3dc8bf1
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1ea8442cc1dd935a65b88ffb95d7e206186e1fb9fc023e698ab89785daa803
+oid sha256:42410dea9cc1279875fd58cdbd387af92a3e6d12f7e52ff497b959ac4ac2873f
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f88b8b4d04735db53bbe5ad9f56393c2fabdec47f79ec07c155c23fa5a121d
+oid sha256:84327cb94481f4aa330fcca0f3bb1121ad581d5beb94e2475a38bda5aca36760
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5775d8fe4f00e8335f10c2f7d4c07d75ee4c0de4fb5b46deba1255765aab4709
+oid sha256:15a861189dd19e0aceec678d8a75cad82c965ce69f5363194a8cdd37ec6a9f5d
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729250c178656dffbc14d6226345620f855971d47f1db880250e47e4b7b142b0
+oid sha256:2e94beadc98ff451c6f6d2bc6f85a9bd66bfdf5599b86c4c582259ad51b083b3
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6464942693710327,
+  "best_metric": 0.6448646187782288,
   "best_model_checkpoint": null,
-  "epoch": 2.0587875076546234,
+  "epoch": 2.1077770973668097,
   "eval_steps": 50,
-  "global_step": 2100,
+  "global_step": 2150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3284,6 +3284,84 @@
       "eval_samples_per_second": 126.157,
       "eval_steps_per_second": 15.778,
       "step": 2100
+    },
+    {
+      "epoch": 2.063686466625842,
+      "grad_norm": 0.23175491392612457,
+      "learning_rate": 7.102482680582014e-05,
+      "loss": 0.6646,
+      "step": 2105
+    },
+    {
+      "epoch": 2.068585425597061,
+      "grad_norm": 0.23201850056648254,
+      "learning_rate": 7.085436623686342e-05,
+      "loss": 0.663,
+      "step": 2110
+    },
+    {
+      "epoch": 2.073484384568279,
+      "grad_norm": 0.23181083798408508,
+      "learning_rate": 7.068374683639328e-05,
+      "loss": 0.6732,
+      "step": 2115
+    },
+    {
+      "epoch": 2.078383343539498,
+      "grad_norm": 0.21368514001369476,
+      "learning_rate": 7.051297035778806e-05,
+      "loss": 0.6602,
+      "step": 2120
+    },
+    {
+      "epoch": 2.0832823025107166,
+      "grad_norm": 0.25182291865348816,
+      "learning_rate": 7.034203855604029e-05,
+      "loss": 0.6544,
+      "step": 2125
+    },
+    {
+      "epoch": 2.0881812614819353,
+      "grad_norm": 0.2292199581861496,
+      "learning_rate": 7.017095318773873e-05,
+      "loss": 0.6522,
+      "step": 2130
+    },
+    {
+      "epoch": 2.0930802204531536,
+      "grad_norm": 0.20745912194252014,
+      "learning_rate": 6.999971601105022e-05,
+      "loss": 0.6527,
+      "step": 2135
+    },
+    {
+      "epoch": 2.0979791794243723,
+      "grad_norm": 0.22758464515209198,
+      "learning_rate": 6.982832878570172e-05,
+      "loss": 0.6578,
+      "step": 2140
+    },
+    {
+      "epoch": 2.102878138395591,
+      "grad_norm": 0.20944316685199738,
+      "learning_rate": 6.965679327296211e-05,
+      "loss": 0.6584,
+      "step": 2145
+    },
+    {
+      "epoch": 2.1077770973668097,
+      "grad_norm": 0.21847444772720337,
+      "learning_rate": 6.94851112356242e-05,
+      "loss": 0.6733,
+      "step": 2150
+    },
+    {
+      "epoch": 2.1077770973668097,
+      "eval_loss": 0.6448646187782288,
+      "eval_runtime": 15.5401,
+      "eval_samples_per_second": 126.061,
+      "eval_steps_per_second": 15.766,
+      "step": 2150
     }
   ],
   "logging_steps": 5,
@@ -3312,7 +3390,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0824270063368929e+18,
+  "total_flos": 1.1081578526120346e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null