Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ae46475882ed1ae504b00be01101d18dae43a1c433764f84c84d69eac63252
+oid sha256:2adcc2abd2157fb60ae9fb647b506419ffcf749d96d577540797eb95581326fa
 size 98088784

last-checkpoint/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442f4c30ec475090cd43f553a9f68a16138c3c60ff13adcc8dfb1a367ebc6600
+size 73939813

last-checkpoint/global_step2500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951d8778340da268ef236cb8a9a23d9d6623d4fe1f188a61fbe08f9098254ed3
+size 73939813

last-checkpoint/global_step2500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a4143fcbe528553de8b626a9a55ab08a186726536821f8d0397e74143dcc38
+size 73939877

last-checkpoint/global_step2500/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:cba209f5c515db450266bb3a7413d4377e882192a8de72815283904b18e5edf8
+size 73939877

last-checkpoint/global_step2500/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f249fa57c54d60decf5afeb96a3baa12044d9c4ac4799cfb6858f33b1839eb
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2450
+global_step2500

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938b777ff3e116c00987a18e1c538cc468155465ad2b958ce3e59986f87ea0ab
+oid sha256:03622e737b0b8bc31e0961f16fb24ed1f36ca068fbf92172955016d36744ba8f
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8cc35976a56bcd3464c4fbaea9853bffe1648d13afd49995ac47e0e617dffe
+oid sha256:8631d6a3a14a1d8ffe0ecd6bcdf565bac306a775dbc9ee116e9cb0ae92390769
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e56364978e3306562b0ad7fc87783d26d5a5559524dec42a78f5fc2a0f1264
+oid sha256:7a6ff2489fd57ce8b4c3e4b6a15142a4393a7355a3116f159e4e45618f906165
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a0a528ef5376d2cc03f230714813daf0eae1d4ead8b3c7e184eb5c7d3228fd
+oid sha256:929048071bdf5eb3856c325b4b779be5c26afd2cebae2821e0d54a31b74a2ad1
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f0cf9f55a2343664c39bbf5f7927b992cc95f4e1e75fa5babbb6ea5b76262f
+oid sha256:2b9eaed5707858cfa6cbc4cad23f1229a605fc99dd72f9963e5671dd9966384a
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6362767219543457,
+  "best_metric": 0.6351883411407471,
   "best_model_checkpoint": null,
-  "epoch": 2.4017146356399266,
+  "epoch": 2.4507042253521125,
   "eval_steps": 50,
-  "global_step": 2450,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3830,6 +3830,84 @@
       "eval_samples_per_second": 126.802,
       "eval_steps_per_second": 15.858,
       "step": 2450
+    },
+    {
+      "epoch": 2.4066135946111453,
+      "grad_norm": 0.21273045241832733,
+      "learning_rate": 5.8806248666594436e-05,
+      "loss": 0.6671,
+      "step": 2455
+    },
+    {
+      "epoch": 2.4115125535823636,
+      "grad_norm": 0.21046888828277588,
+      "learning_rate": 5.862897595233799e-05,
+      "loss": 0.6632,
+      "step": 2460
+    },
+    {
+      "epoch": 2.4164115125535823,
+      "grad_norm": 0.2251223474740982,
+      "learning_rate": 5.845167004136867e-05,
+      "loss": 0.6548,
+      "step": 2465
+    },
+    {
+      "epoch": 2.421310471524801,
+      "grad_norm": 0.2118569016456604,
+      "learning_rate": 5.827433275577903e-05,
+      "loss": 0.6709,
+      "step": 2470
+    },
+    {
+      "epoch": 2.42620943049602,
+      "grad_norm": 0.20193223655223846,
+      "learning_rate": 5.809696591798407e-05,
+      "loss": 0.6616,
+      "step": 2475
+    },
+    {
+      "epoch": 2.431108389467238,
+      "grad_norm": 0.24873106181621552,
+      "learning_rate": 5.7919571350702466e-05,
+      "loss": 0.6734,
+      "step": 2480
+    },
+    {
+      "epoch": 2.436007348438457,
+      "grad_norm": 0.19868969917297363,
+      "learning_rate": 5.774215087693786e-05,
+      "loss": 0.6802,
+      "step": 2485
+    },
+    {
+      "epoch": 2.4409063074096755,
+      "grad_norm": 0.22367221117019653,
+      "learning_rate": 5.7564706319960134e-05,
+      "loss": 0.664,
+      "step": 2490
+    },
+    {
+      "epoch": 2.4458052663808942,
+      "grad_norm": 0.2064606100320816,
+      "learning_rate": 5.7387239503286674e-05,
+      "loss": 0.6595,
+      "step": 2495
+    },
+    {
+      "epoch": 2.4507042253521125,
+      "grad_norm": 0.23037855327129364,
+      "learning_rate": 5.7209752250663576e-05,
+      "loss": 0.6669,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4507042253521125,
+      "eval_loss": 0.6351883411407471,
+      "eval_runtime": 15.5444,
+      "eval_samples_per_second": 126.026,
+      "eval_steps_per_second": 15.761,
+      "step": 2500
     }
   ],
   "logging_steps": 5,
@@ -3858,7 +3936,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.262558980287234e+18,
+  "total_flos": 1.288170288764158e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null