Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d5a9dbbdc09d905b8c60bd36d457096785a0927b4e2e2aabe216ee6ac6c45f
+oid sha256:bd6565301e016283ab568872df6816af131f681b9f5c3f0a097d4f9d809b23f6
 size 29034840

last-checkpoint/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a53c404163e85ff983692ad570f400e43c2847cdd0d069c483a732b36be8d4
+size 43429616

last-checkpoint/global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a03925af6826bf6c00bffcc1584a6359475255347f1f068ef743f7e12c6c9f
+size 43429616

last-checkpoint/global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afe739241a4b9f8fe68c79e7e0a64eb9d2b03897a49eafff1469f818907a43a
+size 43429616

last-checkpoint/global_step100/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:d104230696d55717acd3c2b8a4d72163b534dabb303f6e09895a2f79f4e79a0e
+size 43429616

last-checkpoint/global_step100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d10e19daf23d9a5519105cd8f02b133fd832afdbceaae32bd68ecfb18273f2
+size 637299

last-checkpoint/global_step100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e70d7ddedc58dfdc0ec49a115d1b1e0af3fb290d2785ce1448b9276a2c88d36
+size 637171

last-checkpoint/global_step100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea9021c0781ce4f2bf1279fa5cd2b7bb74cadac2cd292ff41e5bda0c40f8f90
+size 637171

last-checkpoint/global_step100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db256fcff0519e97f39b24fc7b31436bff588b11e7bcc1b1e3b7bba4345a7d67
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step50
+global_step100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe0d720c4c75a6a04213fa3b64bacbe794718a53e2b56ebb67a1a795014dfad
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72452d3138d0ca2ff89429e3294a834ae7a68e8596fc757735ca56ae52509d57
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36e306fb8ebcf53a167bfd6c9af74db410a269ada1e619e3e816f5269543b9d
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb47ce0c6f815a6f8302b0e3819b4c2315ca71dae3138d97fdceb765cdd0a039
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca48e2d3844a29a683fd85ffce1b801b7cef50edd6cbd3fd12220cfd7592690
+oid sha256:f68f3697ebde6b4b610ed5967d76917d2bfd154b81c4fd80c169590521cb7d60
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9254846572875977,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale4/lora/sft/checkpoint-50",
-  "epoch": 0.012876641771825908,
+  "best_metric": 0.9066702723503113,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale4/lora/sft/checkpoint-100",
+  "epoch": 0.025753283543651816,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,11 +96,100 @@
       "eval_steps_per_second": 0.315,
       "num_input_tokens_seen": 518736,
       "step": 50
+    },
+    {
+      "epoch": 0.014164305949008499,
+      "grad_norm": 0.7756988804752654,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 0.8789,
+      "num_input_tokens_seen": 570016,
+      "step": 55
+    },
+    {
+      "epoch": 0.01545197012619109,
+      "grad_norm": 0.6181830544785484,
+      "learning_rate": 0.0001,
+      "loss": 0.8889,
+      "num_input_tokens_seen": 621088,
+      "step": 60
+    },
+    {
+      "epoch": 0.01673963430337368,
+      "grad_norm": 0.48423510573985734,
+      "learning_rate": 9.999525361252996e-05,
+      "loss": 0.8255,
+      "num_input_tokens_seen": 672848,
+      "step": 65
+    },
+    {
+      "epoch": 0.018027298480556272,
+      "grad_norm": 1.0549129101807249,
+      "learning_rate": 9.998101535124758e-05,
+      "loss": 0.8785,
+      "num_input_tokens_seen": 725568,
+      "step": 70
+    },
+    {
+      "epoch": 0.01931496265773886,
+      "grad_norm": 0.5313308413463937,
+      "learning_rate": 9.995728791936504e-05,
+      "loss": 0.8808,
+      "num_input_tokens_seen": 777408,
+      "step": 75
+    },
+    {
+      "epoch": 0.020602626834921454,
+      "grad_norm": 0.6481170197406745,
+      "learning_rate": 9.992407582166581e-05,
+      "loss": 0.7951,
+      "num_input_tokens_seen": 828784,
+      "step": 80
+    },
+    {
+      "epoch": 0.021890291012104043,
+      "grad_norm": 0.8056208046688506,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.7978,
+      "num_input_tokens_seen": 880120,
+      "step": 85
+    },
+    {
+      "epoch": 0.023177955189286635,
+      "grad_norm": 0.6205540239788072,
+      "learning_rate": 9.98292246503335e-05,
+      "loss": 0.8476,
+      "num_input_tokens_seen": 932904,
+      "step": 90
+    },
+    {
+      "epoch": 0.024465619366469224,
+      "grad_norm": 0.7878831511136825,
+      "learning_rate": 9.976760358471686e-05,
+      "loss": 0.8286,
+      "num_input_tokens_seen": 985768,
+      "step": 95
+    },
+    {
+      "epoch": 0.025753283543651816,
+      "grad_norm": 0.9011984281869748,
+      "learning_rate": 9.969653386589748e-05,
+      "loss": 0.8442,
+      "num_input_tokens_seen": 1038064,
+      "step": 100
+    },
+    {
+      "epoch": 0.025753283543651816,
+      "eval_loss": 0.9066702723503113,
+      "eval_runtime": 19.3749,
+      "eval_samples_per_second": 3.097,
+      "eval_steps_per_second": 0.774,
+      "num_input_tokens_seen": 1038064,
+      "step": 100
     }
   ],
   "logging_steps": 5,
   "max_steps": 1200,
-  "num_input_tokens_seen": 518736,
+  "num_input_tokens_seen": 1038064,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -115,7 +204,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 34217743613952.0,
+  "total_flos": 68458302144512.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null