Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2797c1f210babf33d9176582b724813bd513e4ecb9f34e9ad4263b97ef793b1d
+oid sha256:78d6ee2f3cbc4cdb6322476898ecd624062b3c89295c346cbe39f5dde5c2f1ca
 size 98088784

last-checkpoint/global_step2650/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef9e23854e6856d9d004475ee5cef695fb9d4b2bd33e283cfdb2087fa289f45
+size 73939813

last-checkpoint/global_step2650/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5fcc340c9a238aaa1410654c61c0481658e18b800f34620583c3abc03bac8f
+size 73939813

last-checkpoint/global_step2650/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a994ff96e0c66864e0c27860abba85964a20bd8ebdbda88beba053b662cc53a
+size 73939877

last-checkpoint/global_step2650/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e27e40dd0f4be36e5f7317603a3bc7846362efa86f1cf82f088ecc1f686ea6b
+size 73939877

last-checkpoint/global_step2650/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa964d4dba951db0e2bf469732da964f26f429f3ca0bc8b0290df095878d98e8
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2600
+global_step2650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc683c51032187467d8e2977fe5d6f7d1c11ff6fa5bf4be8de498458de0238e
+oid sha256:848a3bab324e767a79a267a7d989130506e36a874e0e4127d7de190f8481ff36
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acfd7b0e90113cc4dbd525d7ea4bdb3da7ff2496ea2ec7c3acd872eeb2536c7f
+oid sha256:20080be7211d83966edb6b3c0a1d6111047cd73e94f53eb27565c9307a2a212e
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1978fca3ff3781ff98e7af0cd64008f614d495cf10474e25db6a72fe6518edb7
+oid sha256:33e203ff29a80c4fd7eec0f580181ca0e442129d3db97917e3c8f0d40bfecd90
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878718bca955848bab18a80adc728f7ef5ee4b3ffe6b5be9a50f36c1101bdaaf
+oid sha256:5c0a80ff898e8e7e6862710635ce5d434aff7f8563552950e7cbca15d4174c7f
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf32410149db3f17625647da9c8b4168efc3a21a2e2e1687015bd006cbc240a
+oid sha256:e3c1fb4651c4fe532f8496df418c3c94914ae6844908aef425566dd85e1002e1
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6326267123222351,
+  "best_metric": 0.6307803988456726,
   "best_model_checkpoint": null,
-  "epoch": 2.548683404776485,
+  "epoch": 2.597672994488671,
   "eval_steps": 50,
-  "global_step": 2600,
+  "global_step": 2650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4064,6 +4064,84 @@
       "eval_samples_per_second": 125.116,
       "eval_steps_per_second": 15.647,
       "step": 2600
+    },
+    {
+      "epoch": 2.5535823637477035,
+      "grad_norm": 0.2051239013671875,
+      "learning_rate": 5.348103053028016e-05,
+      "loss": 0.6639,
+      "step": 2605
+    },
+    {
+      "epoch": 2.5584813227189223,
+      "grad_norm": 0.2549808621406555,
+      "learning_rate": 5.330355532036512e-05,
+      "loss": 0.6612,
+      "step": 2610
+    },
+    {
+      "epoch": 2.563380281690141,
+      "grad_norm": 0.21371757984161377,
+      "learning_rate": 5.312610164067378e-05,
+      "loss": 0.6799,
+      "step": 2615
+    },
+    {
+      "epoch": 2.5682792406613597,
+      "grad_norm": 0.24244041740894318,
+      "learning_rate": 5.294867131481729e-05,
+      "loss": 0.6809,
+      "step": 2620
+    },
+    {
+      "epoch": 2.573178199632578,
+      "grad_norm": 0.21713897585868835,
+      "learning_rate": 5.277126616616671e-05,
+      "loss": 0.657,
+      "step": 2625
+    },
+    {
+      "epoch": 2.5780771586037967,
+      "grad_norm": 0.219580739736557,
+      "learning_rate": 5.259388801783446e-05,
+      "loss": 0.6707,
+      "step": 2630
+    },
+    {
+      "epoch": 2.5829761175750154,
+      "grad_norm": 0.21672317385673523,
+      "learning_rate": 5.241653869265547e-05,
+      "loss": 0.6636,
+      "step": 2635
+    },
+    {
+      "epoch": 2.5878750765462337,
+      "grad_norm": 0.23047353327274323,
+      "learning_rate": 5.2239220013168436e-05,
+      "loss": 0.6701,
+      "step": 2640
+    },
+    {
+      "epoch": 2.5927740355174524,
+      "grad_norm": 0.22297470271587372,
+      "learning_rate": 5.2061933801597145e-05,
+      "loss": 0.6678,
+      "step": 2645
+    },
+    {
+      "epoch": 2.597672994488671,
+      "grad_norm": 0.23974478244781494,
+      "learning_rate": 5.1884681879831726e-05,
+      "loss": 0.6601,
+      "step": 2650
+    },
+    {
+      "epoch": 2.597672994488671,
+      "eval_loss": 0.6307803988456726,
+      "eval_runtime": 15.6073,
+      "eval_samples_per_second": 125.519,
+      "eval_steps_per_second": 15.698,
+      "step": 2650
     }
   ],
   "logging_steps": 5,
@@ -4092,7 +4170,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3404396421298258e+18,
+  "total_flos": 1.3663956002574172e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null