Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaedc144367149e2a92be2a9c0e75df4817558ae00e175c156fbc72ea2ce596
+oid sha256:f6287ca2ed8e9ca31735e5d987ece6f9b430689719f525a3a04c74ff709108ab
 size 29034840

last-checkpoint/global_step800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811cbafedd82a09164ddba198d6c34b0008bf0d647a089b1c2872a336e918a13
+size 43429616

last-checkpoint/global_step800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329da58e74091db53383195c8a404a66ede49ce2e0d0304911e39d4d52c34f6f
+size 43429616

last-checkpoint/global_step800/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e48758f8cd6287cac9729db7c92d3c5b7e5b730e6efd95ccc96f45959761f30
+size 43429616

last-checkpoint/global_step800/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:d67ee88b9ec9a55af37e69be5980321b835195cf4becc47caa8bc10c18c26498
+size 43429616

last-checkpoint/global_step800/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33467f0cec03b4779dee333111c3bd03a22372ddf3a2a795922f0ea80db2d9e0
+size 637299

last-checkpoint/global_step800/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff6501f8b06265046ed0183476dba0c748bb06dda09c2b6e873c247c05ea43d
+size 637171

last-checkpoint/global_step800/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0768848701c35a91de3ad97687565841b9f4771f8101fdde7bedbe1ebcbc9f3
+size 637171

last-checkpoint/global_step800/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4416b108bf4bd22e915b38c44cb62e05b07e52df22336b642b6cf6d7761cbad4
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step750
+global_step800

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b4ef73f3603a1b91082ee108fa8299ebe45fb3cdeec7d0bdca1982af5bf07d
+oid sha256:b4f003069486a57c6ac033f30cf4c4213eb6b7d659bab68a5a50fdb8da7c4118
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882eccb2a272cf97cd645050bd077c971e48e78584f717a1b1cc9b5f1c9326dc
+oid sha256:a016ef89b4392d083b2c15a7cf06a39bc61a759f648cf6dc03f1c32b89a526aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1626bac54f5806a604b7efdd749c5b65d63bbb40fc55c3744aae6130aa24f3de
+oid sha256:9b56fe0893036dc052d18d90feba4328b90ea71561942150b07406ac3d7a700e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40cf83ff997228172cf0b991f9d5209728ccf2f0a75841db5e31e647779a1ad2
+oid sha256:c0c203d12c2c308dab785ed672c9ca27fb6a2f72acd1e1552d1516c7b0006013
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ccf9d8c4b5840071603429d56208abefd14e276e9351f1160a607485df78ae
+oid sha256:5d85b710a5709549c0b4daddcc052f2ed242a5d916ac9ca030c805e7ff501c88
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0033526704646646976,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_scale4/lora/sft/checkpoint-550",
-  "epoch": 0.38629925315477726,
+  "epoch": 0.41205253669842906,
   "eval_steps": 50,
-  "global_step": 750,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1342,11 +1342,100 @@
       "eval_steps_per_second": 0.773,
       "num_input_tokens_seen": 7488000,
       "step": 750
+    },
+    {
+      "epoch": 0.3888745815091424,
+      "grad_norm": 3.511127189174474,
+      "learning_rate": 9.21223287233121e-05,
+      "loss": 0.0426,
+      "num_input_tokens_seen": 7537920,
+      "step": 755
+    },
+    {
+      "epoch": 0.3914499098635076,
+      "grad_norm": 2.858952603531337,
+      "learning_rate": 9.199082286279622e-05,
+      "loss": 0.0094,
+      "num_input_tokens_seen": 7587840,
+      "step": 760
+    },
+    {
+      "epoch": 0.3940252382178728,
+      "grad_norm": 1.9568584051828664,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 0.008,
+      "num_input_tokens_seen": 7637760,
+      "step": 765
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 1.7485145115139782,
+      "learning_rate": 9.172483500792244e-05,
+      "loss": 0.0297,
+      "num_input_tokens_seen": 7687680,
+      "step": 770
+    },
+    {
+      "epoch": 0.39917589492660316,
+      "grad_norm": 0.05161945290023201,
+      "learning_rate": 9.159035930421658e-05,
+      "loss": 0.0239,
+      "num_input_tokens_seen": 7737600,
+      "step": 775
+    },
+    {
+      "epoch": 0.40175122328096835,
+      "grad_norm": 5.343080934932771,
+      "learning_rate": 9.145489998237902e-05,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 7787520,
+      "step": 780
+    },
+    {
+      "epoch": 0.4043265516353335,
+      "grad_norm": 0.020924688334471742,
+      "learning_rate": 9.131846024604274e-05,
+      "loss": 0.0309,
+      "num_input_tokens_seen": 7837440,
+      "step": 785
+    },
+    {
+      "epoch": 0.4069018799896987,
+      "grad_norm": 0.5607043400469908,
+      "learning_rate": 9.11810433220276e-05,
+      "loss": 0.0432,
+      "num_input_tokens_seen": 7887360,
+      "step": 790
+    },
+    {
+      "epoch": 0.40947720834406387,
+      "grad_norm": 0.05221845282486231,
+      "learning_rate": 9.104265246026415e-05,
+      "loss": 0.0022,
+      "num_input_tokens_seen": 7937280,
+      "step": 795
+    },
+    {
+      "epoch": 0.41205253669842906,
+      "grad_norm": 0.09825330413354653,
+      "learning_rate": 9.090329093371666e-05,
+      "loss": 0.0065,
+      "num_input_tokens_seen": 7987200,
+      "step": 800
+    },
+    {
+      "epoch": 0.41205253669842906,
+      "eval_loss": 0.006797688081860542,
+      "eval_runtime": 19.3386,
+      "eval_samples_per_second": 3.103,
+      "eval_steps_per_second": 0.776,
+      "num_input_tokens_seen": 7987200,
+      "step": 800
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 7488000,
+  "num_input_tokens_seen": 7987200,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1361,7 +1450,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 494044521955328.0,
+  "total_flos": 526984501526528.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null