Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ea1db3323fbfc2fcdf43f9fa2ef0ab0320c81b6ef48fc3727aa97d1b9d05c3
+oid sha256:d30836e6cc8e9bc7e6ac4860b9a47462bf2b505763ca8f1f016f00dba39dd063
 size 98088784

last-checkpoint/global_step3050/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec2d173ff3f21519c19c4529cf49015f7351b455919aabd2f92d617dfea800e
+size 73939813

last-checkpoint/global_step3050/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9878bd0908e7cc394ee31cc2cf96c0d61401413d535c5e837df907554c2c3be8
+size 73939813

last-checkpoint/global_step3050/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679f30e0acdc8235795db4f308847a419b26f177124c1a9af50cace3d7f17a2b
+size 73939877

last-checkpoint/global_step3050/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:ef8aa167f419865f888953e5a460286af57c9fd0ce1367970c1958895bac59da
+size 73939877

last-checkpoint/global_step3050/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e7843e59f08e3aa7b5e877697b7647ba9834905436322ba9404fa0a4364927
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step3000
+global_step3050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad15cfeacd5f36c2449b08ba47058a2134999ffa45efc211e7ffd4aebce1a7f
+oid sha256:ea14b9c6b3a6f295496ef7304910c6b324fa957ee6a873aa9c7ba3e19dee7493
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6ef78203d9f455391fc1656ed2cb43336f41e389bc41e4a46bbc8baee83bc3
+oid sha256:5e7e6647b80c88b8b07c192378c0e9cf459bfbb39240b1f97ee2fd33a11b2d76
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a228d42d04cc102c0c1f9f9104aa3d5ea4923c78db588123d41f7cd87db7872
+oid sha256:cb99390398ed2d2ad006f7fe54297d0a309628ca1217f738a1c29766f3fd0e64
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9678b81444b2cc8c0b911ed7e241ed319cf958e011ee1564921f24f2158c7606
+oid sha256:d8f06d95fcd0ec8a7f1f05ddeeb19bb5d11c5c887705f6ecb787b504d8cc2514
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b66c86492a0069dc8985f0926a3b0a40daa6549813a0368d083738441a9d65
+oid sha256:f9b613fc00b8ea63138f8d70379fa6d9a68d4e6248cdb72d56dd145fcca5cc7d
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6234270930290222,
+  "best_metric": 0.6222960948944092,
   "best_model_checkpoint": null,
-  "epoch": 2.9406001224739744,
+  "epoch": 2.9895897121861603,
   "eval_steps": 50,
-  "global_step": 3000,
+  "global_step": 3050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4688,6 +4688,84 @@
       "eval_samples_per_second": 126.096,
       "eval_steps_per_second": 15.77,
       "step": 3000
+    },
+    {
+      "epoch": 2.9454990814451927,
+      "grad_norm": 0.20588572323322296,
+      "learning_rate": 3.95000485078324e-05,
+      "loss": 0.6741,
+      "step": 3005
+    },
+    {
+      "epoch": 2.9503980404164114,
+      "grad_norm": 0.21284903585910797,
+      "learning_rate": 3.9330009094856485e-05,
+      "loss": 0.6438,
+      "step": 3010
+    },
+    {
+      "epoch": 2.95529699938763,
+      "grad_norm": 0.22855360805988312,
+      "learning_rate": 3.916013481191187e-05,
+      "loss": 0.65,
+      "step": 3015
+    },
+    {
+      "epoch": 2.960195958358849,
+      "grad_norm": 0.19158318638801575,
+      "learning_rate": 3.899042740471964e-05,
+      "loss": 0.6593,
+      "step": 3020
+    },
+    {
+      "epoch": 2.9650949173300676,
+      "grad_norm": 0.22519658505916595,
+      "learning_rate": 3.8820888617286e-05,
+      "loss": 0.6542,
+      "step": 3025
+    },
+    {
+      "epoch": 2.969993876301286,
+      "grad_norm": 0.20841963589191437,
+      "learning_rate": 3.865152019188429e-05,
+      "loss": 0.6636,
+      "step": 3030
+    },
+    {
+      "epoch": 2.9748928352725046,
+      "grad_norm": 0.22229060530662537,
+      "learning_rate": 3.8482323869037134e-05,
+      "loss": 0.6698,
+      "step": 3035
+    },
+    {
+      "epoch": 2.9797917942437233,
+      "grad_norm": 0.24960780143737793,
+      "learning_rate": 3.831330138749852e-05,
+      "loss": 0.6707,
+      "step": 3040
+    },
+    {
+      "epoch": 2.9846907532149416,
+      "grad_norm": 0.2418794333934784,
+      "learning_rate": 3.814445448423598e-05,
+      "loss": 0.6524,
+      "step": 3045
+    },
+    {
+      "epoch": 2.9895897121861603,
+      "grad_norm": 0.22541861236095428,
+      "learning_rate": 3.7975784894412676e-05,
+      "loss": 0.659,
+      "step": 3050
+    },
+    {
+      "epoch": 2.9895897121861603,
+      "eval_loss": 0.6222960948944092,
+      "eval_runtime": 15.5064,
+      "eval_samples_per_second": 126.335,
+      "eval_steps_per_second": 15.8,
+      "step": 3050
     }
   ],
   "logging_steps": 5,
@@ -4716,7 +4794,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5470320857624084e+18,
+  "total_flos": 1.5731372043460936e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null