Training in progress, step 2700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe761cb2d0aa677032a1d29dfe42a1dd9a02fe8027a400f98e7c053ab5a8e2d
+oid sha256:c1f0a1299753b652961a95b591427c87ce3772807fe346f4fffff8a783b0e00e
 size 29034840

last-checkpoint/global_step2700/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:ed7e5e674036436364db26c2fb093df880e7161282ad80f1a9ffbcb593cdf0ca
+size 43429616

last-checkpoint/global_step2700/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:deea6f1bbc6224f48319a93c685b88a0c33c58aa2c719b774a866a5849d5a698
+size 43429616

last-checkpoint/global_step2700/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:afb9716aa893ab3fed47090f22d1a7995c1108aa8ddc23cb2e60133fd05a2684
+size 43429616

last-checkpoint/global_step2700/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:b7e86fb385461d99683ba831c08492bbcd24d12057a758987b90e59828f4cd89
+size 43429616

last-checkpoint/global_step2700/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07653c959da414fae2d050ab7f94e043d9c9b24db42c193fdee0c381da235380
+size 637299

last-checkpoint/global_step2700/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cd6d33dfac1715cc7310636621c794fb2c4bc82ea9f78747ff361ddfc2d0bc
+size 637171

last-checkpoint/global_step2700/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b22641256262b58b47ab78d3087c36e2ab93894e42dddb21a15d9010bf7b87
+size 637171

last-checkpoint/global_step2700/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f945c803427e31a4bfb7d69ec05db4391e922a7d4f5c9f65e457b4938ef0f5d
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2650
+global_step2700

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf1e520c0ffd0912cdaf36292baf0834dd187b6292436dd343acbd7d39f37df
+oid sha256:9e599331812a34463d102d64a4034a0b702a893f362f752003aa577fe71dcc1d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480a3937172137fc1b4a3886bc929d7dd5dd0507aebd6b20448e5d03ffe9f33f
+oid sha256:5ed431e5e71393a0174ad2fd492755f8c1142596f1af3bfe7827c1f8f815dd80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc7d6afeed03ecf805019b6cd001604bbcd5e4ef0cbc38e4dc6f5587e48dbf2
+oid sha256:a2e70789f26a9f56b6b779e87cb1a405615af81562a256e5afe579f40972e827
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c0ace59112a18d7f177314d1a9eb2b6b894f2028df1dd368b8c67c8732e18d
+oid sha256:7c8c18bc74d5211e761da269c814d7da0687633993838ec22e81ac939a14e91b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d947631b3ac20358f0fe8d291b46cbd567484f49f979b891836f4ae94e60a2
+oid sha256:375d770aab1911f1464e2da712c8440a47a0edbad49710a4097aa7592f9fdb3e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1869634985923767,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2350",
-  "epoch": 0.7828655834564254,
+  "epoch": 0.7976366322008862,
   "eval_steps": 50,
-  "global_step": 2650,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4724,11 +4724,100 @@
       "eval_steps_per_second": 0.793,
       "num_input_tokens_seen": 27521088,
       "step": 2650
+    },
+    {
+      "epoch": 0.7843426883308715,
+      "grad_norm": 21.321277048653876,
+      "learning_rate": 7.127039815931322e-05,
+      "loss": 0.2047,
+      "num_input_tokens_seen": 27573512,
+      "step": 2655
+    },
+    {
+      "epoch": 0.7858197932053176,
+      "grad_norm": 17.20183228158753,
+      "learning_rate": 7.11598097586445e-05,
+      "loss": 0.2309,
+      "num_input_tokens_seen": 27625488,
+      "step": 2660
+    },
+    {
+      "epoch": 0.7872968980797637,
+      "grad_norm": 1.7315172011761586,
+      "learning_rate": 7.104909511876293e-05,
+      "loss": 0.2188,
+      "num_input_tokens_seen": 27677824,
+      "step": 2665
+    },
+    {
+      "epoch": 0.7887740029542097,
+      "grad_norm": 1.1907445578210916,
+      "learning_rate": 7.0938254900191e-05,
+      "loss": 0.2127,
+      "num_input_tokens_seen": 27730048,
+      "step": 2670
+    },
+    {
+      "epoch": 0.7902511078286558,
+      "grad_norm": 1.81826608908883,
+      "learning_rate": 7.082728976420032e-05,
+      "loss": 0.2534,
+      "num_input_tokens_seen": 27781512,
+      "step": 2675
+    },
+    {
+      "epoch": 0.7917282127031019,
+      "grad_norm": 1.2558672573153766,
+      "learning_rate": 7.071620037280779e-05,
+      "loss": 0.204,
+      "num_input_tokens_seen": 27833808,
+      "step": 2680
+    },
+    {
+      "epoch": 0.793205317577548,
+      "grad_norm": 16.755851819106958,
+      "learning_rate": 7.060498738877159e-05,
+      "loss": 0.2218,
+      "num_input_tokens_seen": 27886232,
+      "step": 2685
+    },
+    {
+      "epoch": 0.794682422451994,
+      "grad_norm": 1.6442173318750486,
+      "learning_rate": 7.049365147558727e-05,
+      "loss": 0.2157,
+      "num_input_tokens_seen": 27938696,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7961595273264401,
+      "grad_norm": 20.30442824896465,
+      "learning_rate": 7.038219329748376e-05,
+      "loss": 0.2401,
+      "num_input_tokens_seen": 27990816,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7976366322008862,
+      "grad_norm": 0.9565866694207389,
+      "learning_rate": 7.027061351941948e-05,
+      "loss": 0.2225,
+      "num_input_tokens_seen": 28042992,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7976366322008862,
+      "eval_loss": 0.41549214720726013,
+      "eval_runtime": 18.9524,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 0.791,
+      "num_input_tokens_seen": 28042992,
+      "step": 2700
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 27521088,
+  "num_input_tokens_seen": 28042992,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -4743,7 +4832,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1815622838124544.0,
+  "total_flos": 1850037045297152.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null