Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f960cc3fc3041049728628ca0f3995042d6d6b849410ccc76854759f1de38e
+oid sha256:686af49d9716db5c977676982b73eead050c55447dd141d1a5c60a378798cf92
 size 98088784

last-checkpoint/global_step2050/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45616c41df00fa1bfbd9ac14ff79e146c79f9632defbfe6dfc06ff18bd55abf8
+size 73939813

last-checkpoint/global_step2050/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:f8b0c02e60bc84e4c5f99dab0099e748a296a98b4797f47b06eb7a9d8d0e1d95
+size 73939813

last-checkpoint/global_step2050/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9179f8475663925d8ca4053d3b76b16cb0678735977baa2c289802bd3353cb81
+size 73939877

last-checkpoint/global_step2050/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812d057a57265c21da7802dcc76e16c7773408a25f3ff1c2fc4c2ce8cdab9440
+size 73939877

last-checkpoint/global_step2050/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f61c444e501f1817872bca2e24f714b3ce7cf6bf9e837542c155318cadca656
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2000
+global_step2050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a14f6a698f92007bbc2dcb792b9b6ca2830509bab22cc9bd34d4e6a2c1d3b8a
+oid sha256:2136a743114bf3ac6a2be5bd25d57e50f3b32784a92a3ed2d3a6f4e8dfe65997
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fdbb189d7242681559cf6c379ca732f316bca39a80295113d8476efdbf2845a
+oid sha256:725ed86be2ad34a12a575d123d89423e1ccfc36d42388d609eed78168e20aa8e
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db64115c44140dcc749fb50ed04400a835cc578facdcfdf170d2c657b74fd53
+oid sha256:aa0c254473a5362fb78028095a7ded74230ab3341cfdf45850d3246e013416c5
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622aa7be447c67092898a74b40ee6e6a8c1fee0783bf1f9c83af0dde5fce5c73
+oid sha256:2a8d80b4bb14ece5fb16e97007c2bfac9158f816b33de1c332f8d229aa7c6235
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8544c996407cdf577fc237cd843a7fc6fa9441fad75c673215c6414edef0e8c3
+oid sha256:76c0ef42f2619bcfd07a1df041b3a7fb00343474a95d72bd4b490c04b2b99687
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6503395438194275,
+  "best_metric": 0.6483769416809082,
   "best_model_checkpoint": null,
-  "epoch": 1.9601959583588489,
+  "epoch": 2.0097979179424375,
   "eval_steps": 50,
-  "global_step": 2000,
+  "global_step": 2050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3128,6 +3128,84 @@
       "eval_samples_per_second": 127.041,
       "eval_steps_per_second": 15.888,
       "step": 2000
+    },
+    {
+      "epoch": 1.9650949173300674,
+      "grad_norm": 0.223761647939682,
+      "learning_rate": 7.439799842198776e-05,
+      "loss": 0.674,
+      "step": 2005
+    },
+    {
+      "epoch": 1.9699938763012859,
+      "grad_norm": 0.19198189675807953,
+      "learning_rate": 7.423108004787508e-05,
+      "loss": 0.6874,
+      "step": 2010
+    },
+    {
+      "epoch": 1.9748928352725046,
+      "grad_norm": 0.20100003480911255,
+      "learning_rate": 7.406396814129006e-05,
+      "loss": 0.6881,
+      "step": 2015
+    },
+    {
+      "epoch": 1.9797917942437233,
+      "grad_norm": 0.22284255921840668,
+      "learning_rate": 7.389666441956613e-05,
+      "loss": 0.6904,
+      "step": 2020
+    },
+    {
+      "epoch": 1.9846907532149418,
+      "grad_norm": 0.2002260684967041,
+      "learning_rate": 7.372917060200785e-05,
+      "loss": 0.6763,
+      "step": 2025
+    },
+    {
+      "epoch": 1.9895897121861603,
+      "grad_norm": 0.21440419554710388,
+      "learning_rate": 7.356148840987336e-05,
+      "loss": 0.6819,
+      "step": 2030
+    },
+    {
+      "epoch": 1.994488671157379,
+      "grad_norm": 0.22840850055217743,
+      "learning_rate": 7.339361956635661e-05,
+      "loss": 0.6935,
+      "step": 2035
+    },
+    {
+      "epoch": 1.9993876301285978,
+      "grad_norm": 0.2073492854833603,
+      "learning_rate": 7.322556579656973e-05,
+      "loss": 0.6927,
+      "step": 2040
+    },
+    {
+      "epoch": 2.0048989589712187,
+      "grad_norm": 0.19991783797740936,
+      "learning_rate": 7.305732882752519e-05,
+      "loss": 0.7925,
+      "step": 2045
+    },
+    {
+      "epoch": 2.0097979179424375,
+      "grad_norm": 0.22880135476589203,
+      "learning_rate": 7.288891038811815e-05,
+      "loss": 0.6637,
+      "step": 2050
+    },
+    {
+      "epoch": 2.0097979179424375,
+      "eval_loss": 0.6483769416809082,
+      "eval_runtime": 15.4537,
+      "eval_samples_per_second": 126.766,
+      "eval_steps_per_second": 15.854,
+      "step": 2050
     }
   ],
   "logging_steps": 5,
@@ -3156,7 +3234,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0314720434234327e+18,
+  "total_flos": 1.0570918347292017e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null