Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2adcc2abd2157fb60ae9fb647b506419ffcf749d96d577540797eb95581326fa
+oid sha256:770e6d839526903ca6b846f534df65727b662e5b56664f96fe6cd955f1dc8822
 size 98088784

last-checkpoint/global_step2550/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21172ee054d5fd4119c31aa22ced2cf7cbc0ccab716a4028aba5d541db875786
+size 73939813

last-checkpoint/global_step2550/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:eca3c8c5fcefdf91dd66a32d4edbd9178ca63659b1d2966ed79a0e72e43f2093
+size 73939813

last-checkpoint/global_step2550/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3242e817ad02e18d3095218502a7cde7a66ac1c7dff5ab716bd0196cc13af0
+size 73939877

last-checkpoint/global_step2550/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:acc076e4938086944fc370a10b991cb2888b4963abb17aba648d408c6310ca63
+size 73939877

last-checkpoint/global_step2550/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4c693e060ff3c438a9b58e892ba4991060d88da653f73e491d17545f3c2957
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2500
+global_step2550

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03622e737b0b8bc31e0961f16fb24ed1f36ca068fbf92172955016d36744ba8f
+oid sha256:66211be425d4da3831f8ac51b4ac9b76c6a16a9fd9028ee5f537668644b51397
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8631d6a3a14a1d8ffe0ecd6bcdf565bac306a775dbc9ee116e9cb0ae92390769
+oid sha256:a0da79439109a7ca4ff852c66d6d76b157ff1736400ce389258ded492e285cb6
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6ff2489fd57ce8b4c3e4b6a15142a4393a7355a3116f159e4e45618f906165
+oid sha256:454d44cf834b4dd8a3667976ff0a436e09d2cfecad46b47a5d331c03fbc98f20
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929048071bdf5eb3856c325b4b779be5c26afd2cebae2821e0d54a31b74a2ad1
+oid sha256:85a76d6d4ecc8a1764784d40c16f9803e82e82729aea9b18d4e1bbc32327d327
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9eaed5707858cfa6cbc4cad23f1229a605fc99dd72f9963e5671dd9966384a
+oid sha256:e7df3463c38c65942460e58d5ffbf4db4eb0600c71f42d3180931fbb2157e70d
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6351883411407471,
+  "best_metric": 0.6343480944633484,
   "best_model_checkpoint": null,
-  "epoch": 2.4507042253521125,
+  "epoch": 2.499693815064299,
   "eval_steps": 50,
-  "global_step": 2500,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3908,6 +3908,84 @@
       "eval_samples_per_second": 126.026,
       "eval_steps_per_second": 15.761,
       "step": 2500
+    },
+    {
+      "epoch": 2.4556031843233312,
+      "grad_norm": 0.2111200988292694,
+      "learning_rate": 5.7032246386046973e-05,
+      "loss": 0.6545,
+      "step": 2505
+    },
+    {
+      "epoch": 2.46050214329455,
+      "grad_norm": 0.22759990394115448,
+      "learning_rate": 5.685472373358426e-05,
+      "loss": 0.6724,
+      "step": 2510
+    },
+    {
+      "epoch": 2.4654011022657687,
+      "grad_norm": 0.23847265541553497,
+      "learning_rate": 5.667718611759539e-05,
+      "loss": 0.6799,
+      "step": 2515
+    },
+    {
+      "epoch": 2.470300061236987,
+      "grad_norm": 0.2177450954914093,
+      "learning_rate": 5.649963536255404e-05,
+      "loss": 0.6525,
+      "step": 2520
+    },
+    {
+      "epoch": 2.4751990202082057,
+      "grad_norm": 0.22332416474819183,
+      "learning_rate": 5.6322073293068914e-05,
+      "loss": 0.6713,
+      "step": 2525
+    },
+    {
+      "epoch": 2.4800979791794244,
+      "grad_norm": 0.19824838638305664,
+      "learning_rate": 5.6144501733865016e-05,
+      "loss": 0.6556,
+      "step": 2530
+    },
+    {
+      "epoch": 2.484996938150643,
+      "grad_norm": 0.20995038747787476,
+      "learning_rate": 5.5966922509764866e-05,
+      "loss": 0.6598,
+      "step": 2535
+    },
+    {
+      "epoch": 2.4898958971218614,
+      "grad_norm": 0.21509043872356415,
+      "learning_rate": 5.578933744566973e-05,
+      "loss": 0.6775,
+      "step": 2540
+    },
+    {
+      "epoch": 2.49479485609308,
+      "grad_norm": 0.2389044612646103,
+      "learning_rate": 5.561174836654091e-05,
+      "loss": 0.6813,
+      "step": 2545
+    },
+    {
+      "epoch": 2.499693815064299,
+      "grad_norm": 0.1885528862476349,
+      "learning_rate": 5.543415709738095e-05,
+      "loss": 0.6614,
+      "step": 2550
+    },
+    {
+      "epoch": 2.499693815064299,
+      "eval_loss": 0.6343480944633484,
+      "eval_runtime": 15.474,
+      "eval_samples_per_second": 126.599,
+      "eval_steps_per_second": 15.833,
+      "step": 2550
     }
   ],
   "logging_steps": 5,
@@ -3936,7 +4014,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.288170288764158e+18,
+  "total_flos": 1.3143227784211988e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null