Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30836e6cc8e9bc7e6ac4860b9a47462bf2b505763ca8f1f016f00dba39dd063
+oid sha256:d3d3618a6549bfada4acfab50184a00e8169ef527f9fd2d6299b8877447758cb
 size 98088784

last-checkpoint/global_step3101/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:e4fb533299f62b9ce25f3ae0988e4c2e58b101d1c5c87106b853300fad700bcf
+size 73939813

last-checkpoint/global_step3101/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6add0427eab5604df8457f0b0c96ae6e13a9298f74b97446cdd0a3e51c32ad
+size 73939813

last-checkpoint/global_step3101/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538f203bc9dec335c9ed3c93f40b10793d873a7700c2c3e88d7e5f29437e5d14
+size 73939877

last-checkpoint/global_step3101/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffb96ff2f8ba9effc52557142b9549943034c6246447792f71e93b98f29a8bf
+size 73939877

last-checkpoint/global_step3101/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c401fb0075566b0e43341ee59679950230715a00367a0f966497bf458e6ba4e
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step3050
+global_step3101

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea14b9c6b3a6f295496ef7304910c6b324fa957ee6a873aa9c7ba3e19dee7493
+oid sha256:9c9f2639515e9a4dbb73442f973fea9b0c88c20b795038a946c56e0e2493ca27
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7e6647b80c88b8b07c192378c0e9cf459bfbb39240b1f97ee2fd33a11b2d76
+oid sha256:ecc1dea28e987710088b449c94c516228a22c7362dc59c8c30f086a46639bae7
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb99390398ed2d2ad006f7fe54297d0a309628ca1217f738a1c29766f3fd0e64
+oid sha256:5887804b4b795f7a573283c1b112d762af0778415a90f4dd264b13d8ce6b6e73
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f06d95fcd0ec8a7f1f05ddeeb19bb5d11c5c887705f6ecb787b504d8cc2514
+oid sha256:d19ad5422c32a302e30ca2b15abb40a89c5c32a5565cad1734400f2ab8b8c060
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b613fc00b8ea63138f8d70379fa6d9a68d4e6248cdb72d56dd145fcca5cc7d
+oid sha256:40dddd77817570d823fe2af41de3280b2532f2b28178ec1ba2cdd4222f46c420
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6222960948944092,
+  "best_metric": 0.620843768119812,
   "best_model_checkpoint": null,
-  "epoch": 2.9895897121861603,
+  "epoch": 3.039191671769749,
   "eval_steps": 50,
-  "global_step": 3050,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4766,6 +4766,84 @@
       "eval_samples_per_second": 126.335,
       "eval_steps_per_second": 15.8,
       "step": 3050
+    },
+    {
+      "epoch": 2.994488671157379,
+      "grad_norm": 0.23352594673633575,
+      "learning_rate": 3.780729435136962e-05,
+      "loss": 0.6777,
+      "step": 3055
+    },
+    {
+      "epoch": 2.9993876301285978,
+      "grad_norm": 0.19848263263702393,
+      "learning_rate": 3.763898458660783e-05,
+      "loss": 0.6618,
+      "step": 3060
+    },
+    {
+      "epoch": 3.0048989589712187,
+      "grad_norm": 0.21553494036197662,
+      "learning_rate": 3.747085732977055e-05,
+      "loss": 0.7689,
+      "step": 3065
+    },
+    {
+      "epoch": 3.0097979179424375,
+      "grad_norm": 0.23350001871585846,
+      "learning_rate": 3.730291430862548e-05,
+      "loss": 0.6462,
+      "step": 3070
+    },
+    {
+      "epoch": 3.0146968769136557,
+      "grad_norm": 0.22312819957733154,
+      "learning_rate": 3.713515724904701e-05,
+      "loss": 0.629,
+      "step": 3075
+    },
+    {
+      "epoch": 3.0195958358848745,
+      "grad_norm": 0.2268122434616089,
+      "learning_rate": 3.696758787499846e-05,
+      "loss": 0.6607,
+      "step": 3080
+    },
+    {
+      "epoch": 3.024494794856093,
+      "grad_norm": 0.22305847704410553,
+      "learning_rate": 3.6800207908514434e-05,
+      "loss": 0.5964,
+      "step": 3085
+    },
+    {
+      "epoch": 3.029393753827312,
+      "grad_norm": 0.23181577026844025,
+      "learning_rate": 3.6633019069683054e-05,
+      "loss": 0.6446,
+      "step": 3090
+    },
+    {
+      "epoch": 3.03429271279853,
+      "grad_norm": 0.2492285519838333,
+      "learning_rate": 3.646602307662833e-05,
+      "loss": 0.6519,
+      "step": 3095
+    },
+    {
+      "epoch": 3.039191671769749,
+      "grad_norm": 0.2302083671092987,
+      "learning_rate": 3.629922164549246e-05,
+      "loss": 0.647,
+      "step": 3100
+    },
+    {
+      "epoch": 3.039191671769749,
+      "eval_loss": 0.620843768119812,
+      "eval_runtime": 15.4094,
+      "eval_samples_per_second": 127.13,
+      "eval_steps_per_second": 15.899,
+      "step": 3100
     }
   ],
   "logging_steps": 5,
@@ -4794,7 +4872,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5731372043460936e+18,
+  "total_flos": 1.5987517748506788e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null